Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.8651. Min Act: -0.1692
Data Index: 5006954 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.8651. Min Act: -0.1698
Data Index: 8669588 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.8482. Min Act: -0.1691
Data Index: 4388838 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.8482. Min Act: -0.1700
Data Index: 7952947 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.8313. Min Act: -0.1691
Data Index: 2398947 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.8228. Min Act: -0.1700
Data Index: 4030905 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.7976. Min Act: -0.1700
Data Index: 2441935 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.7809. Min Act: -0.1691
Data Index: 7177062 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.7559. Min Act: -0.1691
Data Index: 7608393 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.7394. Min Act: -0.1700
Data Index: 6063079 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.7065. Min Act: -0.1699
Data Index: 8128571 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.7147. Min Act: -0.1700
Data Index: 7803698 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.7065. Min Act: -0.1700
Data Index: 2223902 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.6659. Min Act: -0.1699
Data Index: 7309351 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.6902. Min Act: -0.1691
Data Index: 7127031 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.6902. Min Act: -0.1698
Data Index: 4186703 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.6659. Min Act: -0.1700
Data Index: 6732651 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.6740. Min Act: -0.1696
Data Index: 6393694 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.6821. Min Act: -0.1700
Data Index: 3737904 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8651. Min Range: -0.8651
Max Act: 0.6659. Min Act: -0.1699
Data Index: 2273747 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19