Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 454 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.8116. Min Act: -0.1700
Data Index: 3069290 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.7478. Min Act: -0.1700
Data Index: 6102016 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.7319. Min Act: -0.1700
Data Index: 7645874 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.6839. Min Act: -0.1700
Data Index: 4925043 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.6679. Min Act: -0.1700
Data Index: 7738805 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.6518. Min Act: -0.1700
Data Index: 7997655 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.6839. Min Act: -0.1700
Data Index: 6739153 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5875. Min Act: -0.1700
Data Index: 6913577 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5714. Min Act: -0.1700
Data Index: 1451030 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5714. Min Act: -0.1700
Data Index: 4028842 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5714. Min Act: -0.1700
Data Index: 5724856 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5553. Min Act: -0.1700
Data Index: 3866478 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5553. Min Act: -0.1700
Data Index: 7238731 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5714. Min Act: -0.1700
Data Index: 7238991 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5230. Min Act: -0.1700
Data Index: 125337 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5230. Min Act: -0.1700
Data Index: 7818238 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5553. Min Act: -0.1700
Data Index: 5776499 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5230. Min Act: -0.1700
Data Index: 7793845 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5391. Min Act: -0.1700
Data Index: 8046342 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8116. Min Range: -2.8116
Max Act: 2.5553. Min Act: -0.1700
Data Index: 8363366 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19