Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1709 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.6241. Min Act: -0.1700
Data Index: 2624003 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.3116. Min Act: -0.1700
Data Index: 6559385 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.2804. Min Act: -0.1700
Data Index: 3946380 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.1554. Min Act: -0.1700
Data Index: 5626763 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.1866. Min Act: -0.1700
Data Index: 2234963 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.1554. Min Act: -0.1700
Data Index: 8613706 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.0929. Min Act: -0.1700
Data Index: 2309652 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.0929. Min Act: -0.1700
Data Index: 6285028 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.0616. Min Act: -0.1700
Data Index: 1950891 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.0616. Min Act: -0.1700
Data Index: 6331150 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.0616. Min Act: -0.1700
Data Index: 6683142 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.0304. Min Act: -0.1700
Data Index: 8681670 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6241. Min Range: -5.6241
Max Act: 4.9991. Min Act: -0.1700
Data Index: 4205516 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6241. Min Range: -5.6241
Max Act: 5.0304. Min Act: -0.1700
Data Index: 4263248 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6241. Min Range: -5.6241
Max Act: 4.9679. Min Act: -0.1700
Data Index: 7988873 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6241. Min Range: -5.6241
Max Act: 4.9679. Min Act: -0.1700
Data Index: 5308391 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6241. Min Range: -5.6241
Max Act: 4.9366. Min Act: -0.1700
Data Index: 3407449 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6241. Min Range: -5.6241
Max Act: 4.9054. Min Act: -0.1700
Data Index: 6933084 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6241. Min Range: -5.6241
Max Act: 4.9366. Min Act: -0.1700
Data Index: 1535073 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6241. Min Range: -5.6241
Max Act: 4.9054. Min Act: -0.1700
Data Index: 496095 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19