Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 394 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.7228. Min Act: -0.1700
Data Index: 7108981 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.7228. Min Act: -0.1700
Data Index: 7859842 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.3478. Min Act: -0.1700
Data Index: 546400 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.2228. Min Act: -0.1700
Data Index: 7556123 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.2228. Min Act: -0.1700
Data Index: 2870612 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.1603. Min Act: -0.1700
Data Index: 2933632 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.0978. Min Act: -0.1700
Data Index: 6088405 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.0353. Min Act: -0.1700
Data Index: 1033226 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7228. Min Range: -9.7228
Max Act: 9.0353. Min Act: -0.1700
Data Index: 5921573 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.9728. Min Act: -0.1700
Data Index: 3238626 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.9103. Min Act: -0.1700
Data Index: 6232153 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.9103. Min Act: -0.1700
Data Index: 2466613 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.8478. Min Act: -0.1700
Data Index: 3834414 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.8478. Min Act: -0.1700
Data Index: 1996645 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.8478. Min Act: -0.1700
Data Index: 8814547 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.8478. Min Act: -0.1700
Data Index: 8184283 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.7853. Min Act: -0.1700
Data Index: 4159204 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.7853. Min Act: -0.1700
Data Index: 4116914 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.7853. Min Act: -0.1700
Data Index: 6228752 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7228. Min Range: -9.7228
Max Act: 8.7228. Min Act: -0.1700
Data Index: 3802401 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19