Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0786. Min Range: -7.0786
Max Act: 7.0786. Min Act: -0.1700
Data Index: 2517041 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.6411. Min Act: -0.1700
Data Index: 5004833 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.6098. Min Act: -0.1700
Data Index: 196487 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.5786. Min Act: -0.1700
Data Index: 758891 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.5786. Min Act: -0.1700
Data Index: 4456976 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.5473. Min Act: -0.1700
Data Index: 7605463 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.5473. Min Act: -0.1700
Data Index: 7135595 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.5161. Min Act: -0.1700
Data Index: 5698754 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.5161. Min Act: -0.1700
Data Index: 2441405 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4848. Min Act: -0.1700
Data Index: 7489008 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4536. Min Act: -0.1700
Data Index: 7474655 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4536. Min Act: -0.1700
Data Index: 2856551 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4536. Min Act: -0.1700
Data Index: 8509755 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4536. Min Act: -0.1700
Data Index: 1209931 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.3911. Min Act: -0.1700
Data Index: 3217643 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4223. Min Act: -0.1700
Data Index: 3151799 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4223. Min Act: -0.1700
Data Index: 7831089 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4223. Min Act: -0.1700
Data Index: 2175581 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.4223. Min Act: -0.1700
Data Index: 7161148 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0786. Min Range: -7.0786
Max Act: 6.3911. Min Act: -0.1700
Data Index: 4581696 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19