Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1126 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.6361. Min Act: -0.1700
Data Index: 158672 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.5111. Min Act: -0.1700
Data Index: 287528 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.5111. Min Act: -0.1700
Data Index: 5458436 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.4486. Min Act: -0.1700
Data Index: 5256406 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.4174. Min Act: -0.1700
Data Index: 1684493 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.4174. Min Act: -0.1700
Data Index: 6368165 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.3236. Min Act: -0.1700
Data Index: 3755154 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.2611. Min Act: -0.1700
Data Index: 6053576 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.2299. Min Act: -0.1700
Data Index: 870856 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.2299. Min Act: -0.1700
Data Index: 5828013 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.1674. Min Act: -0.1700
Data Index: 3171459 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.1361. Min Act: -0.1700
Data Index: 5930110 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.1674. Min Act: -0.1700
Data Index: 6534355 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.1674. Min Act: -0.1700
Data Index: 353462 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.1361. Min Act: -0.1700
Data Index: 8281891 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.1049. Min Act: -0.1700
Data Index: 4696715 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.0736. Min Act: -0.1700
Data Index: 4788301 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.1049. Min Act: -0.1700
Data Index: 7764175 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.1049. Min Act: -0.1700
Data Index: 3823579 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6361. Min Range: -7.6361
Max Act: 7.0736. Min Act: -0.1700
Data Index: 5424695 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19