Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.9353. Min Act: -0.1700
Data Index: 4319811 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.8728. Min Act: -0.1700
Data Index: 381953 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.8103. Min Act: -0.1700
Data Index: 166438 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.8103. Min Act: -0.1700
Data Index: 2809237 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.7477. Min Act: -0.1700
Data Index: 2342841 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.7164. Min Act: -0.1700
Data Index: 1184419 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.7164. Min Act: -0.1700
Data Index: 4927981 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.7008. Min Act: -0.1700
Data Index: 7088022 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6695. Min Act: -0.1700
Data Index: 4386290 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6851. Min Act: -0.1700
Data Index: 6899528 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6695. Min Act: -0.1700
Data Index: 2438308 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6539. Min Act: -0.1700
Data Index: 8139158 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6695. Min Act: -0.1700
Data Index: 3432339 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6539. Min Act: -0.1700
Data Index: 3809867 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6539. Min Act: -0.1700
Data Index: 7102727 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6226. Min Act: -0.1700
Data Index: 8104719 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6226. Min Act: -0.1700
Data Index: 2710524 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6226. Min Act: -0.1700
Data Index: 4386223 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6069. Min Act: -0.1700
Data Index: 2813397 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9353. Min Range: -3.9353
Max Act: 3.6226. Min Act: -0.1700
Data Index: 3206876 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19