Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.6778. Min Act: -0.1700
Data Index: 4790278 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.6778. Min Act: -0.1700
Data Index: 6119489 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.6465. Min Act: -0.1700
Data Index: 3320620 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.6465. Min Act: -0.1700
Data Index: 2550330 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.5528. Min Act: -0.1700
Data Index: 6648394 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.5215. Min Act: -0.1700
Data Index: 4822772 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.5215. Min Act: -0.1700
Data Index: 7589589 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.5528. Min Act: -0.1700
Data Index: 5917540 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4903. Min Act: -0.1700
Data Index: 8359776 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.5528. Min Act: -0.1700
Data Index: 7043547 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4903. Min Act: -0.1700
Data Index: 2077703 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4903. Min Act: -0.1700
Data Index: 8168559 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4903. Min Act: -0.1700
Data Index: 2830517 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4590. Min Act: -0.1700
Data Index: 7174866 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4590. Min Act: -0.1700
Data Index: 4943472 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4590. Min Act: -0.1700
Data Index: 4444124 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4590. Min Act: -0.1700
Data Index: 1278058 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4590. Min Act: -0.1700
Data Index: 438369 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4590. Min Act: -0.1700
Data Index: 1694213 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6778. Min Range: -5.6778
Max Act: 5.4590. Min Act: -0.1700
Data Index: 8447524 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19