Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4942 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.1548. Min Act: -0.1700
Data Index: 300089 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.1548. Min Act: -0.1700
Data Index: 4249164 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.1236. Min Act: -0.1700
Data Index: 7531640 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.1236. Min Act: -0.1700
Data Index: 3862141 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.1236. Min Act: -0.1700
Data Index: 173325 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0923. Min Act: -0.1700
Data Index: 3172162 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0923. Min Act: -0.1700
Data Index: 2595082 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0611. Min Act: -0.1700
Data Index: 3035719 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0298. Min Act: -0.1700
Data Index: 5256650 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0298. Min Act: -0.1700
Data Index: 485573 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1548. Min Range: -4.1548
Max Act: 4.0611. Min Act: -0.1700
Data Index: 2034736 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9985. Min Act: -0.1700
Data Index: 5120914 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9985. Min Act: -0.1700
Data Index: 2086215 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9985. Min Act: -0.1700
Data Index: 5339790 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9673. Min Act: -0.1700
Data Index: 4809980 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9360. Min Act: -0.1700
Data Index: 3607219 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9673. Min Act: -0.1700
Data Index: 4971964 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9360. Min Act: -0.1700
Data Index: 3281793 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9360. Min Act: -0.1700
Data Index: 7010882 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1548. Min Range: -4.1548
Max Act: 3.9360. Min Act: -0.1700
Data Index: 2151972 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19