Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 412 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.2584. Min Act: -0.1700
Data Index: 582854 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.2271. Min Act: -0.1700
Data Index: 6485677 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.1334. Min Act: -0.1700
Data Index: 3863782 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.1021. Min Act: -0.1700
Data Index: 3378784 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.0709. Min Act: -0.1700
Data Index: 2317525 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.0709. Min Act: -0.1700
Data Index: 3075663 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.0396. Min Act: -0.1700
Data Index: 6785951 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.0396. Min Act: -0.1700
Data Index: 2292424 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.0084. Min Act: -0.1700
Data Index: 8308950 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2584. Min Range: -5.2584
Max Act: 5.0084. Min Act: -0.1700
Data Index: 8555541 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.9459. Min Act: -0.1700
Data Index: 5363551 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.9146. Min Act: -0.1700
Data Index: 3469208 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.9146. Min Act: -0.1700
Data Index: 3766553 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.9146. Min Act: -0.1700
Data Index: 6960163 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.8834. Min Act: -0.1700
Data Index: 3866611 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.8521. Min Act: -0.1700
Data Index: 5869900 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.8521. Min Act: -0.1700
Data Index: 4292393 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.7896. Min Act: -0.1700
Data Index: 8596026 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.8209. Min Act: -0.1700
Data Index: 8375349 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2584. Min Range: -5.2584
Max Act: 4.7896. Min Act: -0.1700
Data Index: 6728229 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19