Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2427 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.4371. Min Act: -0.1700
Data Index: 5940121 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.4058. Min Act: -0.1700
Data Index: 5244574 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2959. Min Act: -0.1700
Data Index: 2812156 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2802. Min Act: -0.1700
Data Index: 3488853 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2645. Min Act: -0.1700
Data Index: 5152836 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2645. Min Act: -0.1700
Data Index: 7321356 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2488. Min Act: -0.1700
Data Index: 2767365 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2174. Min Act: -0.1700
Data Index: 6021976 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2331. Min Act: -0.1700
Data Index: 5589256 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2488. Min Act: -0.1700
Data Index: 2212782 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2331. Min Act: -0.1700
Data Index: 786076 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2331. Min Act: -0.1700
Data Index: 1735085 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2331. Min Act: -0.1700
Data Index: 1220670 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2174. Min Act: -0.1700
Data Index: 7989466 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2174. Min Act: -0.1700
Data Index: 4410136 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2017. Min Act: -0.1700
Data Index: 3922566 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2017. Min Act: -0.1700
Data Index: 5392563 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2174. Min Act: -0.1700
Data Index: 7738021 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.2017. Min Act: -0.1700
Data Index: 4922470 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4371. Min Range: -3.4371
Max Act: 3.1859. Min Act: -0.1700
Data Index: 4707564 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19