Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1384. Min Range: -5.1384
Max Act: 5.1384. Min Act: -0.1700
Data Index: 6134736 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.8571. Min Act: -0.1700
Data Index: 3522870 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.8571. Min Act: -0.1700
Data Index: 8314011 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.7634. Min Act: -0.1700
Data Index: 903483 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.8259. Min Act: -0.1700
Data Index: 10919 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.7634. Min Act: -0.1700
Data Index: 8314017 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.7634. Min Act: -0.1700
Data Index: 5856517 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.7321. Min Act: -0.1700
Data Index: 8314015 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.7321. Min Act: -0.1700
Data Index: 8314019 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.7321. Min Act: -0.1700
Data Index: 3920920 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.7321. Min Act: -0.1700
Data Index: 8314009 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.7009. Min Act: -0.1700
Data Index: 1264234 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.6696. Min Act: -0.1700
Data Index: 7686076 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.6696. Min Act: -0.1700
Data Index: 6642397 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.6071. Min Act: -0.1700
Data Index: 5635590 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.6384. Min Act: -0.1700
Data Index: 2017572 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.6071. Min Act: -0.1700
Data Index: 6892894 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.6071. Min Act: -0.1700
Data Index: 5588840 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.6384. Min Act: -0.1700
Data Index: 5181768 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1384. Min Range: -5.1384
Max Act: 4.6384. Min Act: -0.1700
Data Index: 5563523 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19