Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4461. Min Range: -8.4461
Max Act: 8.4461. Min Act: -0.1700
Data Index: 740823 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4461. Min Range: -8.4461
Max Act: 8.2586. Min Act: -0.1700
Data Index: 1257264 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4461. Min Range: -8.4461
Max Act: 8.1336. Min Act: -0.1700
Data Index: 144993 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4461. Min Range: -8.4461
Max Act: 8.0711. Min Act: -0.1700
Data Index: 979229 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4461. Min Range: -8.4461
Max Act: 8.0086. Min Act: -0.1700
Data Index: 8480906 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4461. Min Range: -8.4461
Max Act: 8.0086. Min Act: -0.1700
Data Index: 3119524 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.9461. Min Act: -0.1700
Data Index: 66583 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.9461. Min Act: -0.1700
Data Index: 7908700 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.9461. Min Act: -0.1700
Data Index: 3914593 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.8836. Min Act: -0.1700
Data Index: 7478801 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.8836. Min Act: -0.1700
Data Index: 5000472 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.8524. Min Act: -0.1700
Data Index: 4236932 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.8211. Min Act: -0.1700
Data Index: 7675842 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.7899. Min Act: -0.1700
Data Index: 6385447 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.7899. Min Act: -0.1700
Data Index: 6876337 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.7586. Min Act: -0.1700
Data Index: 1509852 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.7586. Min Act: -0.1700
Data Index: 7066872 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.7586. Min Act: -0.1700
Data Index: 1738994 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.7274. Min Act: -0.1700
Data Index: 8450357 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4461. Min Range: -8.4461
Max Act: 7.7274. Min Act: -0.1700
Data Index: 5690837 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19