Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7154. Min Range: -7.7154
Max Act: 7.7154. Min Act: -0.1700
Data Index: 8307430 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7154. Min Range: -7.7154
Max Act: 7.0904. Min Act: -0.1700
Data Index: 3641454 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7154. Min Range: -7.7154
Max Act: 7.0592. Min Act: -0.1700
Data Index: 3505290 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7154. Min Range: -7.7154
Max Act: 7.0279. Min Act: -0.1700
Data Index: 7578455 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.9967. Min Act: -0.1700
Data Index: 1584152 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.9654. Min Act: -0.1700
Data Index: 5326902 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.9029. Min Act: -0.1700
Data Index: 2666947 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.9029. Min Act: -0.1700
Data Index: 2923428 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.9029. Min Act: -0.1700
Data Index: 947728 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.9342. Min Act: -0.1700
Data Index: 1531651 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.8717. Min Act: -0.1700
Data Index: 7411584 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.8717. Min Act: -0.1700
Data Index: 8099209 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.8404. Min Act: -0.1700
Data Index: 6568407 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.8404. Min Act: -0.1700
Data Index: 4361783 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.8404. Min Act: -0.1700
Data Index: 7293905 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.8092. Min Act: -0.1700
Data Index: 7519093 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.8404. Min Act: -0.1700
Data Index: 4051812 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.7779. Min Act: -0.1700
Data Index: 6632598 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.7467. Min Act: -0.1700
Data Index: 5830450 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7154. Min Range: -7.7154
Max Act: 6.7154. Min Act: -0.1700
Data Index: 4509163 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19