Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2684 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.9971. Min Act: -0.1700
Data Index: 1058591 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.8721. Min Act: -0.1700
Data Index: 7594203 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.8096. Min Act: -0.1700
Data Index: 5769483 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.5596. Min Act: -0.1700
Data Index: 4425912 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.5596. Min Act: -0.1700
Data Index: 4285918 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.4971. Min Act: -0.1700
Data Index: 7028836 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.4346. Min Act: -0.1700
Data Index: 3409585 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.4346. Min Act: -0.1700
Data Index: 2666047 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.3721. Min Act: -0.1700
Data Index: 4283216 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.3096. Min Act: -0.1700
Data Index: 7779667 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.3721. Min Act: -0.1700
Data Index: 4164011 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.3721. Min Act: -0.1700
Data Index: 5889407 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.3721. Min Act: -0.1700
Data Index: 7041650 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.3721. Min Act: -0.1700
Data Index: 1135805 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.3721. Min Act: -0.1700
Data Index: 2064420 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.3096. Min Act: -0.1700
Data Index: 3074416 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.2471. Min Act: -0.1700
Data Index: 3740765 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.2471. Min Act: -0.1700
Data Index: 3878841 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.2471. Min Act: -0.1700
Data Index: 6519811 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9971. Min Range: -8.9971
Max Act: 8.2471. Min Act: -0.1700
Data Index: 1934188 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19