Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5205. Min Range: -6.5205
Max Act: 6.5205. Min Act: -0.1700
Data Index: 6161624 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.9268. Min Act: -0.1700
Data Index: 991152 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.7705. Min Act: -0.1700
Data Index: 3217808 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.7393. Min Act: -0.1700
Data Index: 4059206 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.7393. Min Act: -0.1700
Data Index: 4398763 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.7393. Min Act: -0.1700
Data Index: 5146824 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.7080. Min Act: -0.1700
Data Index: 6222939 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.6768. Min Act: -0.1700
Data Index: 7038250 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.6143. Min Act: -0.1700
Data Index: 6439341 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.5830. Min Act: -0.1700
Data Index: 4305271 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.5518. Min Act: -0.1700
Data Index: 8016903 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.5518. Min Act: -0.1700
Data Index: 1229043 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.5205. Min Act: -0.1700
Data Index: 7591468 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.5205. Min Act: -0.1700
Data Index: 7463646 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.4893. Min Act: -0.1700
Data Index: 63735 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.4893. Min Act: -0.1700
Data Index: 634914 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.4893. Min Act: -0.1700
Data Index: 720262 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.4580. Min Act: -0.1700
Data Index: 1704348 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.4268. Min Act: -0.1700
Data Index: 6943115 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5205. Min Range: -6.5205
Max Act: 5.3955. Min Act: -0.1700
Data Index: 5080525 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19