Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.2395. Min Act: -0.1700
Data Index: 5876924 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.1770. Min Act: -0.1700
Data Index: 4811854 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.1457. Min Act: -0.1700
Data Index: 6916476 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.1145. Min Act: -0.1700
Data Index: 5876923 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.0832. Min Act: -0.1700
Data Index: 3030787 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.0832. Min Act: -0.1700
Data Index: 4481907 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.0832. Min Act: -0.1700
Data Index: 7024960 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.0207. Min Act: -0.1700
Data Index: 4762911 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9895. Min Act: -0.1700
Data Index: 145892 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.0207. Min Act: -0.1700
Data Index: 4811853 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2395. Min Range: -4.2395
Max Act: 4.0207. Min Act: -0.1700
Data Index: 1750122 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9895. Min Act: -0.1700
Data Index: 435303 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9895. Min Act: -0.1700
Data Index: 5222956 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9895. Min Act: -0.1700
Data Index: 2241106 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9895. Min Act: -0.1700
Data Index: 6055767 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9582. Min Act: -0.1700
Data Index: 4207093 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9582. Min Act: -0.1700
Data Index: 2252722 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9582. Min Act: -0.1700
Data Index: 1067770 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9582. Min Act: -0.1700
Data Index: 1690338 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2395. Min Range: -4.2395
Max Act: 3.9582. Min Act: -0.1700
Data Index: 5626859 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19