Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 100 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1251. Min Range: -6.1251
Max Act: 6.1251. Min Act: -0.1700
Data Index: 6915818 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1251. Min Range: -6.1251
Max Act: 6.0313. Min Act: -0.1700
Data Index: 3500652 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1251. Min Range: -6.1251
Max Act: 6.0313. Min Act: -0.1700
Data Index: 4083707 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1251. Min Range: -6.1251
Max Act: 6.0001. Min Act: -0.1700
Data Index: 3118667 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.9063. Min Act: -0.1700
Data Index: 5357527 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.9376. Min Act: -0.1700
Data Index: 4584187 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.9063. Min Act: -0.1700
Data Index: 4302073 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.8751. Min Act: -0.1700
Data Index: 7323489 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.8751. Min Act: -0.1700
Data Index: 1525580 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.8126. Min Act: -0.1700
Data Index: 298503 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.8438. Min Act: -0.1700
Data Index: 6117496 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.8438. Min Act: -0.1700
Data Index: 5939088 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.8126. Min Act: -0.1700
Data Index: 6656895 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.8126. Min Act: -0.1700
Data Index: 2405286 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.7813. Min Act: -0.1700
Data Index: 4795201 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.7813. Min Act: -0.1700
Data Index: 3980675 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.7501. Min Act: -0.1700
Data Index: 2672304 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.7813. Min Act: -0.1700
Data Index: 2209133 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.7188. Min Act: -0.1700
Data Index: 58533 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1251. Min Range: -6.1251
Max Act: 5.7501. Min Act: -0.1700
Data Index: 6215919 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19