Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5682 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3354. Min Range: -7.3354
Max Act: 7.3354. Min Act: -0.1700
Data Index: 8349717 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3354. Min Range: -7.3354
Max Act: 7.0541. Min Act: -0.1700
Data Index: 2537920 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3354. Min Range: -7.3354
Max Act: 7.0854. Min Act: -0.1700
Data Index: 6687451 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3354. Min Range: -7.3354
Max Act: 7.0229. Min Act: -0.1700
Data Index: 3785782 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.9604. Min Act: -0.1700
Data Index: 8141687 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.8666. Min Act: -0.1700
Data Index: 5106058 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.8354. Min Act: -0.1700
Data Index: 1779543 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.8041. Min Act: -0.1700
Data Index: 6789994 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7729. Min Act: -0.1700
Data Index: 4616191 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7729. Min Act: -0.1700
Data Index: 7008400 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7729. Min Act: -0.1700
Data Index: 8208263 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.8041. Min Act: -0.1700
Data Index: 8611112 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7729. Min Act: -0.1700
Data Index: 1180213 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7729. Min Act: -0.1700
Data Index: 4058322 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7416. Min Act: -0.1700
Data Index: 7446333 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7416. Min Act: -0.1700
Data Index: 943605 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7416. Min Act: -0.1700
Data Index: 7355187 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7416. Min Act: -0.1700
Data Index: 4214093 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7104. Min Act: -0.1700
Data Index: 6700487 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3354. Min Range: -7.3354
Max Act: 6.7104. Min Act: -0.1700
Data Index: 762595 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19