Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1033 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 19.2702. Min Range: -19.2702
Max Act: 19.2702. Min Act: -0.1700
Data Index: 2164536 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.2702. Min Range: -19.2702
Max Act: 18.5202. Min Act: -0.1700
Data Index: 2608841 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.2702. Min Range: -19.2702
Max Act: 18.3952. Min Act: -0.1700
Data Index: 2164541 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.2702. Min Range: -19.2702
Max Act: 18.0202. Min Act: -0.1700
Data Index: 472243 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.7702. Min Act: -0.1700
Data Index: 1064719 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.6452. Min Act: -0.1700
Data Index: 3064315 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.7702. Min Act: -0.1700
Data Index: 7883354 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.7702. Min Act: -0.1700
Data Index: 4759853 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.7702. Min Act: -0.1700
Data Index: 7883356 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.6452. Min Act: -0.1700
Data Index: 8168540 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.6452. Min Act: -0.1700
Data Index: 6464723 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.6452. Min Act: -0.1700
Data Index: 333026 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.5202. Min Act: -0.1700
Data Index: 7868678 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.6452. Min Act: -0.1700
Data Index: 7883346 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.5202. Min Act: -0.1700
Data Index: 8228049 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.5202. Min Act: -0.1700
Data Index: 7883335 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.5202. Min Act: -0.1700
Data Index: 7883347 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.5202. Min Act: -0.1700
Data Index: 7883355 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.5202. Min Act: -0.1700
Data Index: 7883336 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.2702. Min Range: -19.2702
Max Act: 17.2702. Min Act: -0.1700
Data Index: 7883340 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19