Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.7025. Min Act: -0.1700
Data Index: 8651416 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.6555. Min Act: -0.1700
Data Index: 4471833 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.6555. Min Act: -0.1700
Data Index: 452050 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.5303. Min Act: -0.1700
Data Index: 3621826 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.5460. Min Act: -0.1700
Data Index: 2942582 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.5146. Min Act: -0.1700
Data Index: 6309933 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4990. Min Act: -0.1700
Data Index: 8377849 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.5146. Min Act: -0.1700
Data Index: 7182275 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4990. Min Act: -0.1700
Data Index: 6826490 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4833. Min Act: -0.1700
Data Index: 2400357 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4833. Min Act: -0.1700
Data Index: 2299344 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4833. Min Act: -0.1700
Data Index: 3115071 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4520. Min Act: -0.1700
Data Index: 3255554 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4676. Min Act: -0.1700
Data Index: 7042171 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4206. Min Act: -0.1700
Data Index: 7707294 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4676. Min Act: -0.1700
Data Index: 3134143 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4676. Min Act: -0.1700
Data Index: 7031144 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4520. Min Act: -0.1700
Data Index: 4206285 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4833. Min Act: -0.1700
Data Index: 3873687 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7025. Min Range: -3.7025
Max Act: 3.4050. Min Act: -0.1700
Data Index: 3831734 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19