Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.3797. Min Act: -0.1700
Data Index: 6048524 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.3797. Min Act: -0.1700
Data Index: 8604994 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.3172. Min Act: -0.1700
Data Index: 2808284 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.2860. Min Act: -0.1700
Data Index: 7060653 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.2235. Min Act: -0.1700
Data Index: 1816138 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.0672. Min Act: -0.1700
Data Index: 2665006 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.0360. Min Act: -0.1700
Data Index: 7743969 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.0047. Min Act: -0.1700
Data Index: 3123767 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3797. Min Range: -5.3797
Max Act: 5.0047. Min Act: -0.1700
Data Index: 4271470 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.9422. Min Act: -0.1700
Data Index: 8430729 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.9422. Min Act: -0.1700
Data Index: 7715166 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.9422. Min Act: -0.1700
Data Index: 8242768 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.9110. Min Act: -0.1700
Data Index: 2317072 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.9110. Min Act: -0.1700
Data Index: 5384631 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.9110. Min Act: -0.1700
Data Index: 84059 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.9110. Min Act: -0.1700
Data Index: 3980829 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.8797. Min Act: -0.1700
Data Index: 5407663 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.8797. Min Act: -0.1700
Data Index: 3735396 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.8485. Min Act: -0.1700
Data Index: 1749375 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3797. Min Range: -5.3797
Max Act: 4.8797. Min Act: -0.1700
Data Index: 2810813 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19