Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1354. Min Range: -6.1354
Max Act: 6.1354. Min Act: -0.1700
Data Index: 3178527 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1354. Min Range: -6.1354
Max Act: 6.0104. Min Act: -0.1700
Data Index: 513548 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.9791. Min Act: -0.1700
Data Index: 7071387 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.9479. Min Act: -0.1700
Data Index: 182340 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.8541. Min Act: -0.1700
Data Index: 6980617 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.8229. Min Act: -0.1700
Data Index: 5543385 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.8229. Min Act: -0.1700
Data Index: 2543371 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.7916. Min Act: -0.1700
Data Index: 7367783 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.7916. Min Act: -0.1700
Data Index: 8359814 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.7604. Min Act: -0.1700
Data Index: 6432875 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.7604. Min Act: -0.1700
Data Index: 6852392 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.7291. Min Act: -0.1700
Data Index: 4955762 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.7291. Min Act: -0.1700
Data Index: 2986887 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.6979. Min Act: -0.1700
Data Index: 6505307 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.6666. Min Act: -0.1700
Data Index: 2130871 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.6979. Min Act: -0.1700
Data Index: 1300252 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.6354. Min Act: -0.1700
Data Index: 3249422 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.6041. Min Act: -0.1700
Data Index: 168966 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.6666. Min Act: -0.1700
Data Index: 1448101 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1354. Min Range: -6.1354
Max Act: 5.6354. Min Act: -0.1700
Data Index: 1824643 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19