Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6078 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4042. Min Range: -4.4042
Max Act: 4.4042. Min Act: -0.1700
Data Index: 4060504 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4042. Min Range: -4.4042
Max Act: 4.2479. Min Act: -0.1700
Data Index: 7971248 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4042. Min Range: -4.4042
Max Act: 4.1854. Min Act: -0.1700
Data Index: 5564063 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4042. Min Range: -4.4042
Max Act: 4.1229. Min Act: -0.1700
Data Index: 3809915 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4042. Min Range: -4.4042
Max Act: 4.0604. Min Act: -0.1700
Data Index: 371590 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4042. Min Range: -4.4042
Max Act: 4.0916. Min Act: -0.1700
Data Index: 3215142 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4042. Min Range: -4.4042
Max Act: 4.0291. Min Act: -0.1700
Data Index: 3217802 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4042. Min Range: -4.4042
Max Act: 4.0291. Min Act: -0.1700
Data Index: 7512747 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9979. Min Act: -0.1700
Data Index: 1518387 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9666. Min Act: -0.1700
Data Index: 8179201 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9666. Min Act: -0.1700
Data Index: 7786612 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9666. Min Act: -0.1700
Data Index: 2244038 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9353. Min Act: -0.1700
Data Index: 8649154 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9353. Min Act: -0.1700
Data Index: 5308156 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9353. Min Act: -0.1700
Data Index: 2115920 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9041. Min Act: -0.1700
Data Index: 7958588 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1752469 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9041. Min Act: -0.1700
Data Index: 2019469 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.9041. Min Act: -0.1700
Data Index: 2995186 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4042. Min Range: -4.4042
Max Act: 3.8728. Min Act: -0.1700
Data Index: 1737806 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19