Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.5526. Min Act: -0.1700
Data Index: 4985944 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.5056. Min Act: -0.1700
Data Index: 4827453 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4899. Min Act: -0.1700
Data Index: 1403246 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4743. Min Act: -0.1700
Data Index: 559662 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4429. Min Act: -0.1700
Data Index: 2169137 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4272. Min Act: -0.1700
Data Index: 8353208 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4429. Min Act: -0.1700
Data Index: 3050891 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4272. Min Act: -0.1700
Data Index: 2179236 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4429. Min Act: -0.1700
Data Index: 2818946 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4272. Min Act: -0.1700
Data Index: 2452551 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.3959. Min Act: -0.1700
Data Index: 3727169 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4272. Min Act: -0.1700
Data Index: 7873689 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.4116. Min Act: -0.1700
Data Index: 7941779 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.3959. Min Act: -0.1700
Data Index: 3710364 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.3802. Min Act: -0.1700
Data Index: 495143 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.3645. Min Act: -0.1700
Data Index: 5672324 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.3802. Min Act: -0.1700
Data Index: 350731 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.3802. Min Act: -0.1700
Data Index: 7172252 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.3802. Min Act: -0.1700
Data Index: 283514 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5526. Min Range: -3.5526
Max Act: 3.3488. Min Act: -0.1700
Data Index: 8297403 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19