Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5139 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.7381. Min Act: -0.1700
Data Index: 186389 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.6131. Min Act: -0.1700
Data Index: 5149381 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.5818. Min Act: -0.1700
Data Index: 7127098 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.4568. Min Act: -0.1700
Data Index: 464239 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.4568. Min Act: -0.1700
Data Index: 6452187 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.4256. Min Act: -0.1700
Data Index: 1048167 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.3943. Min Act: -0.1700
Data Index: 7100061 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.3631. Min Act: -0.1700
Data Index: 4206277 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.3006. Min Act: -0.1700
Data Index: 3577171 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.3006. Min Act: -0.1700
Data Index: 2735908 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2693. Min Act: -0.1700
Data Index: 6945315 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2693. Min Act: -0.1700
Data Index: 2926101 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2693. Min Act: -0.1700
Data Index: 5514210 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.3006. Min Act: -0.1700
Data Index: 5300381 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2381. Min Act: -0.1700
Data Index: 260404 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2693. Min Act: -0.1700
Data Index: 6602114 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2381. Min Act: -0.1700
Data Index: 7053385 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2693. Min Act: -0.1700
Data Index: 32829 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2068. Min Act: -0.1700
Data Index: 1739835 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7381. Min Range: -5.7381
Max Act: 5.2068. Min Act: -0.1700
Data Index: 3607508 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19