Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.8056. Min Act: -0.1700
Data Index: 5695644 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.7743. Min Act: -0.1700
Data Index: 7524561 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.7431. Min Act: -0.1700
Data Index: 8489655 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.7431. Min Act: -0.1700
Data Index: 3820073 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.6806. Min Act: -0.1700
Data Index: 856390 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.6806. Min Act: -0.1700
Data Index: 4151095 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.6493. Min Act: -0.1700
Data Index: 1110009 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.6493. Min Act: -0.1700
Data Index: 7505114 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.5868. Min Act: -0.1700
Data Index: 5084265 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.5868. Min Act: -0.1700
Data Index: 2093477 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.5868. Min Act: -0.1700
Data Index: 5573251 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.6181. Min Act: -0.1700
Data Index: 3403804 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.5243. Min Act: -0.1700
Data Index: 1730894 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.5556. Min Act: -0.1700
Data Index: 4534352 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.4931. Min Act: -0.1700
Data Index: 5094993 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.5243. Min Act: -0.1700
Data Index: 2758502 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.5243. Min Act: -0.1700
Data Index: 4255536 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.5243. Min Act: -0.1700
Data Index: 3167510 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.4618. Min Act: -0.1700
Data Index: 2896866 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8056. Min Range: -5.8056
Max Act: 5.4931. Min Act: -0.1700
Data Index: 2742167 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19