Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1386 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8693. Min Act: -0.1700
Data Index: 4315135 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8693. Min Act: -0.1700
Data Index: 2807882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8693. Min Act: -0.1700
Data Index: 394762 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 506178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 28984 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 8501054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 7792926 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 7646482 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5914386 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 251275 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5690702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 4297430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5677714 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5415032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5295423 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 652598 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 327209 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 4387532 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8380. Min Act: -0.1700
Data Index: 1875893 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8693. Min Range: -3.8693
Max Act: 3.8068. Min Act: -0.1700
Data Index: 4248519 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19