Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.6457. Min Act: -0.1700
Data Index: 7753623 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.6457. Min Act: -0.1700
Data Index: 1279820 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.5832. Min Act: -0.1700
Data Index: 1033553 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.5520. Min Act: -0.1700
Data Index: 4793897 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.4895. Min Act: -0.1700
Data Index: 8148723 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.4895. Min Act: -0.1700
Data Index: 2243366 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.4895. Min Act: -0.1700
Data Index: 4087119 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.3957. Min Act: -0.1700
Data Index: 5089030 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.3957. Min Act: -0.1700
Data Index: 2603020 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.3645. Min Act: -0.1700
Data Index: 5608194 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.3645. Min Act: -0.1700
Data Index: 1146476 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.3020. Min Act: -0.1700
Data Index: 182726 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.3020. Min Act: -0.1700
Data Index: 5934629 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.3020. Min Act: -0.1700
Data Index: 3460685 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.3020. Min Act: -0.1700
Data Index: 2552538 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.2395. Min Act: -0.1700
Data Index: 6362443 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.2707. Min Act: -0.1700
Data Index: 5244617 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.2707. Min Act: -0.1700
Data Index: 1206918 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.2707. Min Act: -0.1700
Data Index: 1601981 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6457. Min Range: -5.6457
Max Act: 5.2395. Min Act: -0.1700
Data Index: 2150649 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19