Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.9436. Min Act: -0.1700
Data Index: 607426 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.9123. Min Act: -0.1700
Data Index: 2111109 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.8811. Min Act: -0.1700
Data Index: 3705653 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.7873. Min Act: -0.1700
Data Index: 7040635 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.8029. Min Act: -0.1700
Data Index: 6579963 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.7403. Min Act: -0.1700
Data Index: 4586167 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.7091. Min Act: -0.1700
Data Index: 7656724 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.7247. Min Act: -0.1700
Data Index: 6534031 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.7247. Min Act: -0.1700
Data Index: 2157478 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6934. Min Act: -0.1700
Data Index: 3039420 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6778. Min Act: -0.1700
Data Index: 1648607 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6778. Min Act: -0.1700
Data Index: 4548255 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6621. Min Act: -0.1700
Data Index: 4455712 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6778. Min Act: -0.1700
Data Index: 8365526 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6621. Min Act: -0.1700
Data Index: 4302508 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6621. Min Act: -0.1700
Data Index: 815880 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6308. Min Act: -0.1700
Data Index: 4849326 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.6152. Min Act: -0.1700
Data Index: 2219444 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5995. Min Act: -0.1700
Data Index: 4171542 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9436. Min Range: -3.9436
Max Act: 3.5995. Min Act: -0.1700
Data Index: 4486755 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19