Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 587 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0348. Min Range: -4.0348
Max Act: 4.0348. Min Act: -0.1700
Data Index: 3736399 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0348. Min Range: -4.0348
Max Act: 4.0348. Min Act: -0.1700
Data Index: 6571013 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0348. Min Range: -4.0348
Max Act: 4.0035. Min Act: -0.1700
Data Index: 1035640 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0348. Min Range: -4.0348
Max Act: 4.0035. Min Act: -0.1700
Data Index: 8117174 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9723. Min Act: -0.1700
Data Index: 5315080 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9723. Min Act: -0.1700
Data Index: 4052257 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9723. Min Act: -0.1700
Data Index: 2139705 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9723. Min Act: -0.1700
Data Index: 3595059 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9410. Min Act: -0.1700
Data Index: 8163335 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8785. Min Act: -0.1700
Data Index: 4316899 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9097. Min Act: -0.1700
Data Index: 1059812 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8785. Min Act: -0.1700
Data Index: 4255798 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8785. Min Act: -0.1700
Data Index: 7246959 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8472. Min Act: -0.1700
Data Index: 4213643 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8472. Min Act: -0.1700
Data Index: 4883254 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8472. Min Act: -0.1700
Data Index: 4037050 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.7847. Min Act: -0.1700
Data Index: 6932407 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8159. Min Act: -0.1700
Data Index: 146494 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8159. Min Act: -0.1700
Data Index: 3796173 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8159. Min Act: -0.1700
Data Index: 3311605 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19