Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2499 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.6538. Min Act: -0.1700
Data Index: 7268941 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.5288. Min Act: -0.1700
Data Index: 5039397 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.4350. Min Act: -0.1700
Data Index: 2531781 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.4350. Min Act: -0.1700
Data Index: 586827 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.4350. Min Act: -0.1700
Data Index: 2852696 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.4350. Min Act: -0.1700
Data Index: 4919240 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.4038. Min Act: -0.1700
Data Index: 4291051 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.4038. Min Act: -0.1700
Data Index: 4345549 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.4038. Min Act: -0.1700
Data Index: 2494049 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3725. Min Act: -0.1700
Data Index: 8617319 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3725. Min Act: -0.1700
Data Index: 5374262 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3725. Min Act: -0.1700
Data Index: 7009236 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.4038. Min Act: -0.1700
Data Index: 7397262 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3725. Min Act: -0.1700
Data Index: 5443727 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3100. Min Act: -0.1700
Data Index: 2166425 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3413. Min Act: -0.1700
Data Index: 4035191 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3725. Min Act: -0.1700
Data Index: 334343 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3413. Min Act: -0.1700
Data Index: 7591724 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3413. Min Act: -0.1700
Data Index: 378842 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6538. Min Range: -4.6538
Max Act: 4.3100. Min Act: -0.1700
Data Index: 851670 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19