Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6131 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.9366. Min Act: -0.1700
Data Index: 1820221 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.8741. Min Act: -0.1700
Data Index: 1460504 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.8741. Min Act: -0.1700
Data Index: 28695 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.8116. Min Act: -0.1700
Data Index: 3788944 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.8741. Min Act: -0.1700
Data Index: 6635377 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.7804. Min Act: -0.1700
Data Index: 1088813 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.8429. Min Act: -0.1700
Data Index: 3675617 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.8429. Min Act: -0.1700
Data Index: 3401722 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.7804. Min Act: -0.1700
Data Index: 6604431 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.7179. Min Act: -0.1700
Data Index: 541538 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.7491. Min Act: -0.1700
Data Index: 7520407 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.7491. Min Act: -0.1700
Data Index: 608043 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.7179. Min Act: -0.1700
Data Index: 2431425 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.6866. Min Act: -0.1700
Data Index: 117964 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.6866. Min Act: -0.1700
Data Index: 93086 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.6554. Min Act: -0.1700
Data Index: 7699756 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.6554. Min Act: -0.1700
Data Index: 3243029 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.6866. Min Act: -0.1700
Data Index: 4433861 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.6241. Min Act: -0.1700
Data Index: 7307221 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9366. Min Range: -7.9366
Max Act: 7.6866. Min Act: -0.1700
Data Index: 3066249 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19