Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6698178 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.1674. Min Act: -0.1700
Data Index: 6842045 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.1049. Min Act: -0.1700
Data Index: 3476914 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0424. Min Act: -0.1700
Data Index: 1356976 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0111. Min Act: -0.1700
Data Index: 4319201 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0111. Min Act: -0.1700
Data Index: 7134740 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 8244441 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 5286524 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 7374566 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 6903143 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 1399264 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9486. Min Act: -0.1700
Data Index: 8217602 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 4680390 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 1923631 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 3061517 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.8861. Min Act: -0.1700
Data Index: 6940489 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 5764439 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 1289902 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 3835906 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 4881777 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19