Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.8309. Min Act: -0.1700
Data Index: 6421520 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7684. Min Act: -0.1700
Data Index: 3399898 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7372. Min Act: -0.1700
Data Index: 6062230 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7684. Min Act: -0.1700
Data Index: 2207045 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7372. Min Act: -0.1700
Data Index: 5351209 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7372. Min Act: -0.1700
Data Index: 7610288 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7684. Min Act: -0.1700
Data Index: 4924448 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7372. Min Act: -0.1700
Data Index: 1041978 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.8309. Min Act: -0.1700
Data Index: 8028937 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7372. Min Act: -0.1700
Data Index: 2378175 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.7059. Min Act: -0.1700
Data Index: 8035384 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6747. Min Act: -0.1700
Data Index: 3872216 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6434. Min Act: -0.1700
Data Index: 651803 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6747. Min Act: -0.1700
Data Index: 1686298 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6434. Min Act: -0.1700
Data Index: 4379838 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6122. Min Act: -0.1700
Data Index: 2502098 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5809. Min Act: -0.1700
Data Index: 7524105 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6122. Min Act: -0.1700
Data Index: 4924449 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.5809. Min Act: -0.1700
Data Index: 5362689 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8309. Min Range: -4.8309
Max Act: 4.6122. Min Act: -0.1700
Data Index: 4377109 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19