Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2286. Min Range: -4.2286
Max Act: 4.2286. Min Act: -0.1700
Data Index: 5315113 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2286. Min Range: -4.2286
Max Act: 4.1661. Min Act: -0.1700
Data Index: 262059 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.9473. Min Act: -0.1700
Data Index: 6229143 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8847. Min Act: -0.1700
Data Index: 4232941 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8847. Min Act: -0.1700
Data Index: 5801369 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.9160. Min Act: -0.1700
Data Index: 5873076 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.9160. Min Act: -0.1700
Data Index: 2629315 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8535. Min Act: -0.1700
Data Index: 6870663 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8222. Min Act: -0.1700
Data Index: 2338188 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7909. Min Act: -0.1700
Data Index: 3554249 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8222. Min Act: -0.1700
Data Index: 8034758 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7909. Min Act: -0.1700
Data Index: 7822025 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7909. Min Act: -0.1700
Data Index: 7467827 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8222. Min Act: -0.1700
Data Index: 223760 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8222. Min Act: -0.1700
Data Index: 5506833 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.8535. Min Act: -0.1700
Data Index: 888646 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7596. Min Act: -0.1700
Data Index: 4034402 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7596. Min Act: -0.1700
Data Index: 38718 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7596. Min Act: -0.1700
Data Index: 3392873 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2286. Min Range: -4.2286
Max Act: 3.7909. Min Act: -0.1700
Data Index: 3905077 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19