Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3328 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.9336. Min Act: -0.1700
Data Index: 1952472 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.9019. Min Act: -0.1700
Data Index: 4915713 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8384. Min Act: -0.1700
Data Index: 1314139 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8384. Min Act: -0.1700
Data Index: 2605342 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8384. Min Act: -0.1700
Data Index: 8614179 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8384. Min Act: -0.1700
Data Index: 8220329 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8225. Min Act: -0.1700
Data Index: 4375069 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8225. Min Act: -0.1700
Data Index: 3359037 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8225. Min Act: -0.1700
Data Index: 1917772 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8066. Min Act: -0.1700
Data Index: 628223 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.8225. Min Act: -0.1700
Data Index: 7109395 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7907. Min Act: -0.1700
Data Index: 3892255 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7747. Min Act: -0.1700
Data Index: 95954 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7747. Min Act: -0.1700
Data Index: 6692497 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7747. Min Act: -0.1700
Data Index: 8038418 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7588. Min Act: -0.1700
Data Index: 8396503 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7588. Min Act: -0.1700
Data Index: 8428833 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7588. Min Act: -0.1700
Data Index: 2463207 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7588. Min Act: -0.1700
Data Index: 3537081 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9336. Min Range: -2.9336
Max Act: 2.7588. Min Act: -0.1700
Data Index: 7066533 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19