Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 115 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.9155. Min Act: -0.1700
Data Index: 2001064 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.8218. Min Act: -0.1700
Data Index: 5345982 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7905. Min Act: -0.1700
Data Index: 1945827 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.8218. Min Act: -0.1700
Data Index: 3349634 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7593. Min Act: -0.1700
Data Index: 7375944 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.8218. Min Act: -0.1700
Data Index: 4475112 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7593. Min Act: -0.1700
Data Index: 4677622 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7905. Min Act: -0.1700
Data Index: 5548498 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7905. Min Act: -0.1700
Data Index: 5996524 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7593. Min Act: -0.1700
Data Index: 7485125 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7593. Min Act: -0.1700
Data Index: 5249884 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7593. Min Act: -0.1700
Data Index: 3935435 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7593. Min Act: -0.1700
Data Index: 1301889 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7280. Min Act: -0.1700
Data Index: 6763831 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7280. Min Act: -0.1700
Data Index: 3578446 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7593. Min Act: -0.1700
Data Index: 2347834 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.6968. Min Act: -0.1700
Data Index: 3304413 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.6968. Min Act: -0.1700
Data Index: 7203010 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7280. Min Act: -0.1700
Data Index: 3917899 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9155. Min Range: -6.9155
Max Act: 6.7593. Min Act: -0.1700
Data Index: 391211 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19