Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3871. Min Range: -9.3871
Max Act: 9.3871. Min Act: -0.1700
Data Index: 3885993 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3871. Min Range: -9.3871
Max Act: 9.1996. Min Act: -0.1700
Data Index: 309791 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3871. Min Range: -9.3871
Max Act: 9.1371. Min Act: -0.1700
Data Index: 5372190 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3871. Min Range: -9.3871
Max Act: 9.1371. Min Act: -0.1700
Data Index: 5053837 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3871. Min Range: -9.3871
Max Act: 9.0121. Min Act: -0.1700
Data Index: 7601010 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3871. Min Range: -9.3871
Max Act: 9.0746. Min Act: -0.1700
Data Index: 6465807 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3871. Min Range: -9.3871
Max Act: 9.0121. Min Act: -0.1700
Data Index: 6847982 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3871. Min Range: -9.3871
Max Act: 9.0121. Min Act: -0.1700
Data Index: 3275366 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.8871. Min Act: -0.1700
Data Index: 4371206 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.8871. Min Act: -0.1700
Data Index: 7947490 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.8871. Min Act: -0.1700
Data Index: 1266089 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.8246. Min Act: -0.1700
Data Index: 6297268 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.7621. Min Act: -0.1700
Data Index: 533864 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.7621. Min Act: -0.1700
Data Index: 4882425 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.6996. Min Act: -0.1700
Data Index: 7463933 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.6996. Min Act: -0.1700
Data Index: 4137817 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.6371. Min Act: -0.1700
Data Index: 4052557 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.6996. Min Act: -0.1700
Data Index: 1832415 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.6371. Min Act: -0.1700
Data Index: 914580 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3871. Min Range: -9.3871
Max Act: 8.6371. Min Act: -0.1700
Data Index: 7023354 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19