Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8346. Min Range: -7.8346
Max Act: 7.8346. Min Act: -0.1700
Data Index: 230493 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8346. Min Range: -7.8346
Max Act: 7.1783. Min Act: -0.1700
Data Index: 7002771 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8346. Min Range: -7.8346
Max Act: 7.0533. Min Act: -0.1700
Data Index: 5827834 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8346. Min Range: -7.8346
Max Act: 7.0533. Min Act: -0.1700
Data Index: 648250 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8346. Min Range: -7.8346
Max Act: 7.0533. Min Act: -0.1700
Data Index: 8315328 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8346. Min Range: -7.8346
Max Act: 7.0221. Min Act: -0.1700
Data Index: 1280272 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.9596. Min Act: -0.1700
Data Index: 230491 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.9596. Min Act: -0.1700
Data Index: 6241780 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.9596. Min Act: -0.1700
Data Index: 2296890 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.9283. Min Act: -0.1700
Data Index: 6756166 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.9596. Min Act: -0.1700
Data Index: 4133958 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.9283. Min Act: -0.1700
Data Index: 815708 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.8971. Min Act: -0.1700
Data Index: 8674661 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.8971. Min Act: -0.1700
Data Index: 8568652 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.8346. Min Act: -0.1700
Data Index: 1428001 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.8346. Min Act: -0.1700
Data Index: 3161120 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.8033. Min Act: -0.1700
Data Index: 486954 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.8033. Min Act: -0.1700
Data Index: 5057172 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.7721. Min Act: -0.1700
Data Index: 4201029 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8346. Min Range: -7.8346
Max Act: 6.7408. Min Act: -0.1700
Data Index: 7234334 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19