Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.4209. Min Act: -0.1700
Data Index: 7690969 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.4209. Min Act: -0.1700
Data Index: 8803120 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.3584. Min Act: -0.1700
Data Index: 1229986 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.2959. Min Act: -0.1700
Data Index: 4227932 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.2959. Min Act: -0.1700
Data Index: 2833937 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.2334. Min Act: -0.1700
Data Index: 403473 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.1709. Min Act: -0.1700
Data Index: 7561250 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.2334. Min Act: -0.1700
Data Index: 8163039 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.1709. Min Act: -0.1700
Data Index: 5979696 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.1709. Min Act: -0.1700
Data Index: 6660534 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.1709. Min Act: -0.1700
Data Index: 782918 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.1084. Min Act: -0.1700
Data Index: 7131071 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.1084. Min Act: -0.1700
Data Index: 6011542 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.1084. Min Act: -0.1700
Data Index: 4119267 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.0459. Min Act: -0.1700
Data Index: 529391 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4209. Min Range: -8.4209
Max Act: 8.0459. Min Act: -0.1700
Data Index: 8075199 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4209. Min Range: -8.4209
Max Act: 7.9834. Min Act: -0.1700
Data Index: 6352987 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4209. Min Range: -8.4209
Max Act: 7.9834. Min Act: -0.1700
Data Index: 277250 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4209. Min Range: -8.4209
Max Act: 7.9834. Min Act: -0.1700
Data Index: 6162482 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4209. Min Range: -8.4209
Max Act: 7.9834. Min Act: -0.1700
Data Index: 3031830 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19