Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3833 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.9283. Min Act: -0.1700
Data Index: 607567 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.8807. Min Act: -0.1700
Data Index: 7790432 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7694. Min Act: -0.1700
Data Index: 1384598 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7853. Min Act: -0.1700
Data Index: 6698508 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7694. Min Act: -0.1700
Data Index: 4335665 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7534. Min Act: -0.1700
Data Index: 2279912 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7534. Min Act: -0.1700
Data Index: 3274917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7534. Min Act: -0.1700
Data Index: 6891761 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7375. Min Act: -0.1700
Data Index: 396800 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7375. Min Act: -0.1700
Data Index: 2848106 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7215. Min Act: -0.1700
Data Index: 8270307 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7055. Min Act: -0.1700
Data Index: 3188539 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.6895. Min Act: -0.1700
Data Index: 7783236 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7055. Min Act: -0.1700
Data Index: 1074217 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.6895. Min Act: -0.1700
Data Index: 3140706 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.6895. Min Act: -0.1700
Data Index: 561709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.6895. Min Act: -0.1700
Data Index: 3199918 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.6895. Min Act: -0.1700
Data Index: 3639262 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.6895. Min Act: -0.1700
Data Index: 3743662 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.6895. Min Act: -0.1700
Data Index: 4488270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19