Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 446 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0466. Min Range: -3.0466
Max Act: 3.0466. Min Act: -0.1700
Data Index: 4114007 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.9834. Min Act: -0.1700
Data Index: 1443942 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.9676. Min Act: -0.1700
Data Index: 6441641 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.9518. Min Act: -0.1700
Data Index: 2597721 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.9518. Min Act: -0.1700
Data Index: 254498 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.9359. Min Act: -0.1700
Data Index: 2366006 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8884. Min Act: -0.1700
Data Index: 2755360 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.9042. Min Act: -0.1700
Data Index: 3514253 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8884. Min Act: -0.1700
Data Index: 4412635 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8884. Min Act: -0.1700
Data Index: 4825727 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8884. Min Act: -0.1700
Data Index: 2161304 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8884. Min Act: -0.1700
Data Index: 2211848 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8566. Min Act: -0.1700
Data Index: 7059110 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8884. Min Act: -0.1700
Data Index: 2431526 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8407. Min Act: -0.1700
Data Index: 5495616 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8566. Min Act: -0.1700
Data Index: 5401695 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8566. Min Act: -0.1700
Data Index: 4932174 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8407. Min Act: -0.1700
Data Index: 2036041 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8566. Min Act: -0.1700
Data Index: 471363 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0466. Min Range: -3.0466
Max Act: 2.8407. Min Act: -0.1700
Data Index: 5209972 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19