Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5916 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.8373. Min Act: -0.1700
Data Index: 7792141 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.6185. Min Act: -0.1700
Data Index: 5299787 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.5560. Min Act: -0.1700
Data Index: 7731021 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.5560. Min Act: -0.1700
Data Index: 4383518 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.5248. Min Act: -0.1700
Data Index: 901578 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.5248. Min Act: -0.1700
Data Index: 7825725 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.5560. Min Act: -0.1700
Data Index: 8710185 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.4310. Min Act: -0.1700
Data Index: 4852690 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.4310. Min Act: -0.1700
Data Index: 3730578 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.3998. Min Act: -0.1700
Data Index: 6432959 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.3998. Min Act: -0.1700
Data Index: 3703511 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.3685. Min Act: -0.1700
Data Index: 2593471 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.3685. Min Act: -0.1700
Data Index: 1492543 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.3373. Min Act: -0.1700
Data Index: 48536 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.3060. Min Act: -0.1700
Data Index: 33553 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.2748. Min Act: -0.1700
Data Index: 5839251 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.2748. Min Act: -0.1700
Data Index: 13338 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.2748. Min Act: -0.1700
Data Index: 4392215 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.2435. Min Act: -0.1700
Data Index: 4988507 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8373. Min Range: -6.8373
Max Act: 6.2435. Min Act: -0.1700
Data Index: 5059593 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19