Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1015. Min Range: -10.1015
Max Act: 10.1015. Min Act: -0.1700
Data Index: 4819445 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1015. Min Range: -10.1015
Max Act: 9.7890. Min Act: -0.1700
Data Index: 275943 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1015. Min Range: -10.1015
Max Act: 9.6640. Min Act: -0.1700
Data Index: 6746332 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1015. Min Range: -10.1015
Max Act: 9.6015. Min Act: -0.1700
Data Index: 4534113 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1015. Min Range: -10.1015
Max Act: 9.2890. Min Act: -0.1700
Data Index: 5294318 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1015. Min Range: -10.1015
Max Act: 9.2265. Min Act: -0.1700
Data Index: 7304825 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1015. Min Range: -10.1015
Max Act: 9.1640. Min Act: -0.1700
Data Index: 1384743 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1015. Min Range: -10.1015
Max Act: 9.0390. Min Act: -0.1700
Data Index: 8384678 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1015. Min Range: -10.1015
Max Act: 9.0390. Min Act: -0.1700
Data Index: 6862341 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.9765. Min Act: -0.1700
Data Index: 232587 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.9765. Min Act: -0.1700
Data Index: 6202629 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.9140. Min Act: -0.1700
Data Index: 1700632 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.9140. Min Act: -0.1700
Data Index: 7827971 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.9140. Min Act: -0.1700
Data Index: 1690180 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.9140. Min Act: -0.1700
Data Index: 7790070 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.7890. Min Act: -0.1700
Data Index: 1430355 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.8515. Min Act: -0.1700
Data Index: 7790060 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.8515. Min Act: -0.1700
Data Index: 5828412 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.8515. Min Act: -0.1700
Data Index: 1533799 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1015. Min Range: -10.1015
Max Act: 8.8515. Min Act: -0.1700
Data Index: 4594584 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19