Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3745 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.1332. Min Act: -0.1700
Data Index: 1339326 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0859. Min Act: -0.1700
Data Index: 2930786 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0701. Min Act: -0.1700
Data Index: 3296104 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0701. Min Act: -0.1700
Data Index: 7760586 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0701. Min Act: -0.1700
Data Index: 11665 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0544. Min Act: -0.1700
Data Index: 3947495 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0228. Min Act: -0.1700
Data Index: 3213356 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0228. Min Act: -0.1700
Data Index: 4834857 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0228. Min Act: -0.1700
Data Index: 6494522 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0070. Min Act: -0.1700
Data Index: 314448 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0070. Min Act: -0.1700
Data Index: 4472740 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0070. Min Act: -0.1700
Data Index: 8078898 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0070. Min Act: -0.1700
Data Index: 649334 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9912. Min Act: -0.1700
Data Index: 4755653 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9754. Min Act: -0.1700
Data Index: 5095654 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9912. Min Act: -0.1700
Data Index: 5845341 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9912. Min Act: -0.1700
Data Index: 4788121 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9754. Min Act: -0.1700
Data Index: 8013064 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9754. Min Act: -0.1700
Data Index: 2949593 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9754. Min Act: -0.1700
Data Index: 1975818 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19