Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 567 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3010. Min Range: -7.3010
Max Act: 7.3010. Min Act: -0.1700
Data Index: 7588370 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.8010. Min Act: -0.1700
Data Index: 3236512 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.8323. Min Act: -0.1700
Data Index: 6055030 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.7073. Min Act: -0.1700
Data Index: 2901332 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.6448. Min Act: -0.1700
Data Index: 8159822 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.5823. Min Act: -0.1700
Data Index: 6262659 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.5510. Min Act: -0.1700
Data Index: 7482064 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.5198. Min Act: -0.1700
Data Index: 5438753 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4885. Min Act: -0.1700
Data Index: 8503084 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.5198. Min Act: -0.1700
Data Index: 4952984 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4885. Min Act: -0.1700
Data Index: 2713367 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4885. Min Act: -0.1700
Data Index: 1499960 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4885. Min Act: -0.1700
Data Index: 5436833 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4573. Min Act: -0.1700
Data Index: 6526222 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.3948. Min Act: -0.1700
Data Index: 7093327 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4260. Min Act: -0.1700
Data Index: 842574 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4260. Min Act: -0.1700
Data Index: 5865661 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4573. Min Act: -0.1700
Data Index: 301779 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.4260. Min Act: -0.1700
Data Index: 1015409 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3010. Min Range: -7.3010
Max Act: 6.3635. Min Act: -0.1700
Data Index: 2852837 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19