Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1034 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.3296. Min Act: -0.1700
Data Index: 2204216 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.1734. Min Act: -0.1700
Data Index: 8153543 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0796. Min Act: -0.1700
Data Index: 2884569 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0796. Min Act: -0.1700
Data Index: 4838849 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0796. Min Act: -0.1700
Data Index: 1477669 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0484. Min Act: -0.1700
Data Index: 6825893 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0484. Min Act: -0.1700
Data Index: 6434540 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0484. Min Act: -0.1700
Data Index: 3838768 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0484. Min Act: -0.1700
Data Index: 3269887 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0171. Min Act: -0.1700
Data Index: 4156098 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0171. Min Act: -0.1700
Data Index: 600823 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9859. Min Act: -0.1700
Data Index: 6065995 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9859. Min Act: -0.1700
Data Index: 1418026 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9859. Min Act: -0.1700
Data Index: 4396632 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 5619087 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 8766545 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 6532234 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 6608985 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 3825309 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9234. Min Act: -0.1700
Data Index: 136513 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19