Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2301 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.4483. Min Act: -0.1700
Data Index: 3922704 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.4171. Min Act: -0.1700
Data Index: 6939547 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.3858. Min Act: -0.1700
Data Index: 6870245 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.4171. Min Act: -0.1700
Data Index: 4065537 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.3546. Min Act: -0.1700
Data Index: 8018630 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.3233. Min Act: -0.1700
Data Index: 635341 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2608. Min Act: -0.1700
Data Index: 1560254 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2608. Min Act: -0.1700
Data Index: 3506225 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2608. Min Act: -0.1700
Data Index: 4496319 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2608. Min Act: -0.1700
Data Index: 3602204 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2608. Min Act: -0.1700
Data Index: 3632793 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2296. Min Act: -0.1700
Data Index: 5120103 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2296. Min Act: -0.1700
Data Index: 6669803 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2296. Min Act: -0.1700
Data Index: 2751913 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.1983. Min Act: -0.1700
Data Index: 3216527 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.1983. Min Act: -0.1700
Data Index: 765621 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.2296. Min Act: -0.1700
Data Index: 6176262 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.1983. Min Act: -0.1700
Data Index: 7306075 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.1670. Min Act: -0.1700
Data Index: 4374398 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4483. Min Range: -4.4483
Max Act: 4.1670. Min Act: -0.1700
Data Index: 3323476 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19