Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1580 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3490. Min Range: -7.3490
Max Act: 7.3490. Min Act: -0.1700
Data Index: 6160459 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3490. Min Range: -7.3490
Max Act: 7.0678. Min Act: -0.1700
Data Index: 3491905 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3490. Min Range: -7.3490
Max Act: 7.0053. Min Act: -0.1700
Data Index: 6617779 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.9115. Min Act: -0.1700
Data Index: 8357197 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.8803. Min Act: -0.1700
Data Index: 1126379 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.8178. Min Act: -0.1700
Data Index: 5358996 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.8178. Min Act: -0.1700
Data Index: 4231998 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.8178. Min Act: -0.1700
Data Index: 6946823 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.8178. Min Act: -0.1700
Data Index: 1407261 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.7865. Min Act: -0.1700
Data Index: 6060456 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.7553. Min Act: -0.1700
Data Index: 2097795 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.7553. Min Act: -0.1700
Data Index: 1616159 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.7240. Min Act: -0.1700
Data Index: 7239227 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.6928. Min Act: -0.1700
Data Index: 5268468 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.6615. Min Act: -0.1700
Data Index: 4053395 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.6928. Min Act: -0.1700
Data Index: 1496401 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.6615. Min Act: -0.1700
Data Index: 1764160 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.6615. Min Act: -0.1700
Data Index: 4750441 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.6615. Min Act: -0.1700
Data Index: 4013496 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3490. Min Range: -7.3490
Max Act: 6.6303. Min Act: -0.1700
Data Index: 7086525 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19