Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 610 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.5604. Min Act: -0.1700
Data Index: 8473274 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.5292. Min Act: -0.1700
Data Index: 1075959 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4979. Min Act: -0.1700
Data Index: 8263298 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4979. Min Act: -0.1700
Data Index: 4098758 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4979. Min Act: -0.1700
Data Index: 4523385 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4979. Min Act: -0.1700
Data Index: 8473277 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4979. Min Act: -0.1700
Data Index: 8657472 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.5292. Min Act: -0.1700
Data Index: 3256389 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.5292. Min Act: -0.1700
Data Index: 3658331 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4979. Min Act: -0.1700
Data Index: 7203764 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4667. Min Act: -0.1700
Data Index: 8227520 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4667. Min Act: -0.1700
Data Index: 8224565 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4667. Min Act: -0.1700
Data Index: 7623988 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4667. Min Act: -0.1700
Data Index: 3894511 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4667. Min Act: -0.1700
Data Index: 6584374 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4667. Min Act: -0.1700
Data Index: 5816608 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4667. Min Act: -0.1700
Data Index: 1730289 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4667. Min Act: -0.1700
Data Index: 4184561 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4354. Min Act: -0.1700
Data Index: 2002990 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5604. Min Range: -4.5604
Max Act: 4.4354. Min Act: -0.1700
Data Index: 3133337 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19