Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3852 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.9281. Min Act: -0.1700
Data Index: 5810450 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.5218. Min Act: -0.1700
Data Index: 268862 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.5218. Min Act: -0.1700
Data Index: 6437935 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.4593. Min Act: -0.1700
Data Index: 3893288 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.3968. Min Act: -0.1700
Data Index: 5935565 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.4593. Min Act: -0.1700
Data Index: 3472249 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.4281. Min Act: -0.1700
Data Index: 825020 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.3656. Min Act: -0.1700
Data Index: 6095344 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.3031. Min Act: -0.1700
Data Index: 2678942 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.3031. Min Act: -0.1700
Data Index: 8173048 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.3343. Min Act: -0.1700
Data Index: 8771249 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.3031. Min Act: -0.1700
Data Index: 2295228 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.2718. Min Act: -0.1700
Data Index: 8749359 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.2718. Min Act: -0.1700
Data Index: 869780 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.2718. Min Act: -0.1700
Data Index: 869776 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.2406. Min Act: -0.1700
Data Index: 4979195 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.2406. Min Act: -0.1700
Data Index: 4139257 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.2718. Min Act: -0.1700
Data Index: 6170989 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.2093. Min Act: -0.1700
Data Index: 4923977 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9281. Min Range: -6.9281
Max Act: 6.1468. Min Act: -0.1700
Data Index: 862165 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19