Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0472. Min Range: -3.0472
Max Act: 3.0314. Min Act: -0.1700
Data Index: 7676176 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0472. Min Range: -3.0472
Max Act: 3.0314. Min Act: -0.1700
Data Index: 5118699 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0472. Min Range: -3.0472
Max Act: 3.0472. Min Act: -0.1700
Data Index: 4936483 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0472. Min Range: -3.0472
Max Act: 3.0314. Min Act: -0.1700
Data Index: 4912475 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9998. Min Act: -0.1700
Data Index: 1459272 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9998. Min Act: -0.1700
Data Index: 1558001 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0472. Min Range: -3.0472
Max Act: 3.0156. Min Act: -0.1700
Data Index: 568285 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9998. Min Act: -0.1700
Data Index: 69918 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9682. Min Act: -0.1700
Data Index: 2531716 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9682. Min Act: -0.1700
Data Index: 3680901 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9682. Min Act: -0.1700
Data Index: 94842 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9682. Min Act: -0.1700
Data Index: 8408119 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9365. Min Act: -0.1700
Data Index: 6718388 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9682. Min Act: -0.1700
Data Index: 8563568 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9207. Min Act: -0.1700
Data Index: 1749123 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9365. Min Act: -0.1700
Data Index: 44049 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9207. Min Act: -0.1700
Data Index: 469834 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9365. Min Act: -0.1700
Data Index: 5771769 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9365. Min Act: -0.1700
Data Index: 2444794 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0472. Min Range: -3.0472
Max Act: 2.9524. Min Act: -0.1700
Data Index: 6992309 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19