Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0826. Min Range: -6.0826
Max Act: 6.0826. Min Act: -0.1700
Data Index: 8570997 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0826. Min Range: -6.0826
Max Act: 6.0201. Min Act: -0.1700
Data Index: 3488326 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.9263. Min Act: -0.1700
Data Index: 3636203 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.9263. Min Act: -0.1700
Data Index: 1121258 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.8638. Min Act: -0.1700
Data Index: 5302015 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.7701. Min Act: -0.1700
Data Index: 3076399 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.7388. Min Act: -0.1700
Data Index: 5534673 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.7076. Min Act: -0.1700
Data Index: 8480916 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.7076. Min Act: -0.1700
Data Index: 7605473 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6763. Min Act: -0.1700
Data Index: 5511999 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.7076. Min Act: -0.1700
Data Index: 6126919 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6763. Min Act: -0.1700
Data Index: 8137522 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6451. Min Act: -0.1700
Data Index: 3229834 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6451. Min Act: -0.1700
Data Index: 3041568 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6451. Min Act: -0.1700
Data Index: 1953930 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6451. Min Act: -0.1700
Data Index: 1864577 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6451. Min Act: -0.1700
Data Index: 302713 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6763. Min Act: -0.1700
Data Index: 1668517 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6138. Min Act: -0.1700
Data Index: 1479755 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0826. Min Range: -6.0826
Max Act: 5.6138. Min Act: -0.1700
Data Index: 3754240 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19