Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2395. Min Range: -6.2395
Max Act: 6.2395. Min Act: -0.1700
Data Index: 6875499 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2395. Min Range: -6.2395
Max Act: 6.0520. Min Act: -0.1700
Data Index: 7276157 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.8020. Min Act: -0.1700
Data Index: 7187319 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.8020. Min Act: -0.1700
Data Index: 5994882 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.7707. Min Act: -0.1700
Data Index: 6864516 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.6770. Min Act: -0.1700
Data Index: 7124424 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.6770. Min Act: -0.1700
Data Index: 673425 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 1688321 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.6457. Min Act: -0.1700
Data Index: 3730728 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 8675992 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.5832. Min Act: -0.1700
Data Index: 801302 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.5207. Min Act: -0.1700
Data Index: 1534007 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.5520. Min Act: -0.1700
Data Index: 3767428 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.5207. Min Act: -0.1700
Data Index: 5796875 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.4895. Min Act: -0.1700
Data Index: 2910985 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.4582. Min Act: -0.1700
Data Index: 3587204 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.4895. Min Act: -0.1700
Data Index: 983185 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.4582. Min Act: -0.1700
Data Index: 3263332 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.4582. Min Act: -0.1700
Data Index: 7548520 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2395. Min Range: -6.2395
Max Act: 5.4582. Min Act: -0.1700
Data Index: 849270 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19