Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.6114. Min Act: -0.1700
Data Index: 3400855 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.5801. Min Act: -0.1700
Data Index: 4379430 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.5489. Min Act: -0.1700
Data Index: 397808 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.5176. Min Act: -0.1700
Data Index: 8288015 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.5176. Min Act: -0.1700
Data Index: 3876774 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.5176. Min Act: -0.1700
Data Index: 3852601 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4864. Min Act: -0.1700
Data Index: 6978089 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4864. Min Act: -0.1700
Data Index: 4193303 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4864. Min Act: -0.1700
Data Index: 289800 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4551. Min Act: -0.1700
Data Index: 6889386 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4551. Min Act: -0.1700
Data Index: 3597447 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4551. Min Act: -0.1700
Data Index: 2864912 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4551. Min Act: -0.1700
Data Index: 8287998 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4239. Min Act: -0.1700
Data Index: 7476639 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4239. Min Act: -0.1700
Data Index: 6121610 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4239. Min Act: -0.1700
Data Index: 5675840 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4239. Min Act: -0.1700
Data Index: 3328327 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4239. Min Act: -0.1700
Data Index: 2808860 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.4239. Min Act: -0.1700
Data Index: 8776872 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.3614. Min Act: -0.1700
Data Index: 1720759 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19