Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 911 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.4433. Min Act: -0.1700
Data Index: 371494 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.4433. Min Act: -0.1700
Data Index: 310805 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.4120. Min Act: -0.1700
Data Index: 2674027 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.4120. Min Act: -0.1700
Data Index: 5894160 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3808. Min Act: -0.1700
Data Index: 7817549 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.4120. Min Act: -0.1700
Data Index: 7562304 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3495. Min Act: -0.1700
Data Index: 4948842 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3808. Min Act: -0.1700
Data Index: 2541292 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3808. Min Act: -0.1700
Data Index: 6972615 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3808. Min Act: -0.1700
Data Index: 2243966 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3495. Min Act: -0.1700
Data Index: 7297804 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3495. Min Act: -0.1700
Data Index: 4702137 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3495. Min Act: -0.1700
Data Index: 4287553 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3808. Min Act: -0.1700
Data Index: 2326558 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3495. Min Act: -0.1700
Data Index: 7071449 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3495. Min Act: -0.1700
Data Index: 3571024 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3495. Min Act: -0.1700
Data Index: 8759446 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3183. Min Act: -0.1700
Data Index: 3366737 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3183. Min Act: -0.1700
Data Index: 4902680 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.3183. Min Act: -0.1700
Data Index: 7372465 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19