Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1694 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0652. Min Range: -12.0652
Max Act: 12.0652. Min Act: -0.1700
Data Index: 4272240 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0652. Min Range: -12.0652
Max Act: 11.6277. Min Act: -0.1700
Data Index: 5707461 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0652. Min Range: -12.0652
Max Act: 11.2527. Min Act: -0.1700
Data Index: 5843453 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0652. Min Range: -12.0652
Max Act: 11.2527. Min Act: -0.1700
Data Index: 4531073 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0652. Min Range: -12.0652
Max Act: 11.1277. Min Act: -0.1700
Data Index: 5814055 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.9402. Min Act: -0.1700
Data Index: 7546410 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.9402. Min Act: -0.1700
Data Index: 6941583 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.8777. Min Act: -0.1700
Data Index: 7006294 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.8777. Min Act: -0.1700
Data Index: 4546086 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.8152. Min Act: -0.1700
Data Index: 1890880 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.8152. Min Act: -0.1700
Data Index: 7172027 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.8152. Min Act: -0.1700
Data Index: 2640473 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.8152. Min Act: -0.1700
Data Index: 7657868 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.8152. Min Act: -0.1700
Data Index: 2937647 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.6902. Min Act: -0.1700
Data Index: 2680555 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.7527. Min Act: -0.1700
Data Index: 295679 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.6902. Min Act: -0.1700
Data Index: 8226593 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.6902. Min Act: -0.1700
Data Index: 4211127 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.6902. Min Act: -0.1700
Data Index: 1377630 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0652. Min Range: -12.0652
Max Act: 10.6902. Min Act: -0.1700
Data Index: 2681396 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19