Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.6534. Min Act: -0.1700
Data Index: 479999 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.4659. Min Act: -0.1700
Data Index: 5112480 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.4659. Min Act: -0.1700
Data Index: 2746198 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.4034. Min Act: -0.1700
Data Index: 6690325 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.1221. Min Act: -0.1700
Data Index: 6367165 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.1221. Min Act: -0.1700
Data Index: 471524 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.0909. Min Act: -0.1700
Data Index: 100725 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.0909. Min Act: -0.1700
Data Index: 6208873 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.0596. Min Act: -0.1700
Data Index: 8070614 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.0596. Min Act: -0.1700
Data Index: 6286160 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6534. Min Range: -8.6534
Max Act: 8.0284. Min Act: -0.1700
Data Index: 5641161 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9971. Min Act: -0.1700
Data Index: 7334449 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9971. Min Act: -0.1700
Data Index: 363459 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9659. Min Act: -0.1700
Data Index: 1444049 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9659. Min Act: -0.1700
Data Index: 2289710 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9346. Min Act: -0.1700
Data Index: 4386613 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9346. Min Act: -0.1700
Data Index: 7051916 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9346. Min Act: -0.1700
Data Index: 2289728 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9034. Min Act: -0.1700
Data Index: 4070994 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6534. Min Range: -8.6534
Max Act: 7.9034. Min Act: -0.1700
Data Index: 6503427 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19