Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5896 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0520. Min Range: -4.0520
Max Act: 4.0208. Min Act: -0.1700
Data Index: 3834228 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0520. Min Range: -4.0520
Max Act: 4.0520. Min Act: -0.1700
Data Index: 8055714 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.7863. Min Act: -0.1700
Data Index: 5104626 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.7863. Min Act: -0.1700
Data Index: 3342013 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.6924. Min Act: -0.1700
Data Index: 3342012 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.6768. Min Act: -0.1700
Data Index: 1364453 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.6768. Min Act: -0.1700
Data Index: 4540343 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.6298. Min Act: -0.1700
Data Index: 7292157 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.6142. Min Act: -0.1700
Data Index: 8055715 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5985. Min Act: -0.1700
Data Index: 2539007 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.6142. Min Act: -0.1700
Data Index: 8041288 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.6142. Min Act: -0.1700
Data Index: 6004969 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5985. Min Act: -0.1700
Data Index: 2706895 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5985. Min Act: -0.1700
Data Index: 8009515 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5985. Min Act: -0.1700
Data Index: 4847007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5985. Min Act: -0.1700
Data Index: 1703888 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5985. Min Act: -0.1700
Data Index: 6322009 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5672. Min Act: -0.1700
Data Index: 7970952 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5516. Min Act: -0.1700
Data Index: 8093458 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0520. Min Range: -4.0520
Max Act: 3.5672. Min Act: -0.1700
Data Index: 427669 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19