Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.4137. Min Act: -0.1700
Data Index: 1265054 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.3155. Min Act: -0.1700
Data Index: 8059024 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.1999. Min Act: -0.1700
Data Index: 3103391 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.2165. Min Act: -0.1700
Data Index: 7824592 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.1333. Min Act: -0.1700
Data Index: 1201340 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0831. Min Act: -0.1700
Data Index: 5520123 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0999. Min Act: -0.1700
Data Index: 3569875 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0999. Min Act: -0.1700
Data Index: 2556885 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0831. Min Act: -0.1700
Data Index: 3413742 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0663. Min Act: -0.1700
Data Index: 1199928 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0327. Min Act: -0.1700
Data Index: 5346129 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0663. Min Act: -0.1700
Data Index: 1037204 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0495. Min Act: -0.1700
Data Index: 2931036 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0495. Min Act: -0.1700
Data Index: 2072800 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0327. Min Act: -0.1700
Data Index: 8381187 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0495. Min Act: -0.1700
Data Index: 8820990 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0327. Min Act: -0.1700
Data Index: 8193520 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0327. Min Act: -0.1700
Data Index: 4175842 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0327. Min Act: -0.1700
Data Index: 5335683 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4137. Min Range: -2.4137
Max Act: 2.0158. Min Act: -0.1700
Data Index: 7578479 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19