Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6341 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1656. Min Range: -4.1656
Max Act: 4.1656. Min Act: -0.1700
Data Index: 3388890 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1656. Min Range: -4.1656
Max Act: 4.0406. Min Act: -0.1700
Data Index: 6184834 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.8530. Min Act: -0.1700
Data Index: 8618073 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.8217. Min Act: -0.1700
Data Index: 642660 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.7748. Min Act: -0.1700
Data Index: 140768 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.7592. Min Act: -0.1700
Data Index: 6941267 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.7279. Min Act: -0.1700
Data Index: 7177777 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.7279. Min Act: -0.1700
Data Index: 2071728 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.7123. Min Act: -0.1700
Data Index: 6642919 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.7123. Min Act: -0.1700
Data Index: 610346 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6966. Min Act: -0.1700
Data Index: 8425854 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6810. Min Act: -0.1700
Data Index: 8289106 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6810. Min Act: -0.1700
Data Index: 4008136 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6653. Min Act: -0.1700
Data Index: 6097150 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6653. Min Act: -0.1700
Data Index: 2014215 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6810. Min Act: -0.1700
Data Index: 5571834 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6497. Min Act: -0.1700
Data Index: 83691 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6497. Min Act: -0.1700
Data Index: 4226933 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6340. Min Act: -0.1700
Data Index: 3900379 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.6340. Min Act: -0.1700
Data Index: 8143679 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19