Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.6777. Min Act: -0.1700
Data Index: 1092463 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.6777. Min Act: -0.1700
Data Index: 8142947 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.6621. Min Act: -0.1700
Data Index: 6461075 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.6464. Min Act: -0.1700
Data Index: 7518148 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.6152. Min Act: -0.1700
Data Index: 1348900 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.5682. Min Act: -0.1700
Data Index: 4360381 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.5682. Min Act: -0.1700
Data Index: 6657396 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.5369. Min Act: -0.1700
Data Index: 8007270 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.5212. Min Act: -0.1700
Data Index: 1561304 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.4899. Min Act: -0.1700
Data Index: 848542 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.4742. Min Act: -0.1700
Data Index: 5563208 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.4899. Min Act: -0.1700
Data Index: 5612753 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.4899. Min Act: -0.1700
Data Index: 2859122 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.5056. Min Act: -0.1700
Data Index: 5879704 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.4742. Min Act: -0.1700
Data Index: 2870147 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.4429. Min Act: -0.1700
Data Index: 5292809 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.4115. Min Act: -0.1700
Data Index: 5130791 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.3959. Min Act: -0.1700
Data Index: 6140224 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.4272. Min Act: -0.1700
Data Index: 6667604 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6777. Min Range: -3.6777
Max Act: 3.3959. Min Act: -0.1700
Data Index: 4746649 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19