Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.7619. Min Act: -0.1700
Data Index: 5705048 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.7619. Min Act: -0.1700
Data Index: 7965683 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.7463. Min Act: -0.1700
Data Index: 2333646 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.7307. Min Act: -0.1700
Data Index: 286113 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6994. Min Act: -0.1700
Data Index: 4795055 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6524. Min Act: -0.1700
Data Index: 1893117 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6524. Min Act: -0.1700
Data Index: 2651395 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6837. Min Act: -0.1700
Data Index: 8571556 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6524. Min Act: -0.1700
Data Index: 1454289 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6368. Min Act: -0.1700
Data Index: 4210117 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6368. Min Act: -0.1700
Data Index: 5930614 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6368. Min Act: -0.1700
Data Index: 5926497 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6211. Min Act: -0.1700
Data Index: 1459063 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6211. Min Act: -0.1700
Data Index: 7736610 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6524. Min Act: -0.1700
Data Index: 2350531 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6524. Min Act: -0.1700
Data Index: 286114 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6055. Min Act: -0.1700
Data Index: 7183974 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6211. Min Act: -0.1700
Data Index: 4763779 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6055. Min Act: -0.1700
Data Index: 6497891 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7619. Min Range: -3.7619
Max Act: 3.6055. Min Act: -0.1700
Data Index: 2730682 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19