Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4948 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0477. Min Range: -6.0477
Max Act: 6.0477. Min Act: -0.1700
Data Index: 103191 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.9227. Min Act: -0.1700
Data Index: 405781 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.6727. Min Act: -0.1700
Data Index: 8333797 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.5477. Min Act: -0.1700
Data Index: 3150101 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.5477. Min Act: -0.1700
Data Index: 1586329 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.5477. Min Act: -0.1700
Data Index: 7823128 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.5477. Min Act: -0.1700
Data Index: 4029699 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.5164. Min Act: -0.1700
Data Index: 7098187 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.5164. Min Act: -0.1700
Data Index: 428167 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.5164. Min Act: -0.1700
Data Index: 8516449 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.5164. Min Act: -0.1700
Data Index: 5404431 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.4852. Min Act: -0.1700
Data Index: 3878010 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.4852. Min Act: -0.1700
Data Index: 1458631 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.4539. Min Act: -0.1700
Data Index: 1305211 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.4539. Min Act: -0.1700
Data Index: 1208079 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.4227. Min Act: -0.1700
Data Index: 1127450 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.3914. Min Act: -0.1700
Data Index: 3601455 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.3914. Min Act: -0.1700
Data Index: 1436362 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.3914. Min Act: -0.1700
Data Index: 6557004 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0477. Min Range: -6.0477
Max Act: 5.3602. Min Act: -0.1700
Data Index: 2596994 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19