Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4603 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.7466. Min Act: -0.1700
Data Index: 3009902 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.7466. Min Act: -0.1700
Data Index: 8149813 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.6216. Min Act: -0.1700
Data Index: 7864138 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.6216. Min Act: -0.1700
Data Index: 8820210 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.5279. Min Act: -0.1700
Data Index: 5817585 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.5279. Min Act: -0.1700
Data Index: 6483790 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.4966. Min Act: -0.1700
Data Index: 6278140 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.4966. Min Act: -0.1700
Data Index: 2428282 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.4654. Min Act: -0.1700
Data Index: 7486077 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.4341. Min Act: -0.1700
Data Index: 347640 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.4341. Min Act: -0.1700
Data Index: 1965319 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.4654. Min Act: -0.1700
Data Index: 3210651 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.4029. Min Act: -0.1700
Data Index: 5211407 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.3716. Min Act: -0.1700
Data Index: 555812 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.4029. Min Act: -0.1700
Data Index: 7654493 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.3716. Min Act: -0.1700
Data Index: 8345204 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.3716. Min Act: -0.1700
Data Index: 2253799 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.3716. Min Act: -0.1700
Data Index: 4584234 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.3716. Min Act: -0.1700
Data Index: 1677791 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7466. Min Range: -6.7466
Max Act: 6.3404. Min Act: -0.1700
Data Index: 892404 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19