Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 399 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2440. Min Range: -5.2440
Max Act: 5.2440. Min Act: -0.1700
Data Index: 5682474 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2440. Min Range: -5.2440
Max Act: 5.0878. Min Act: -0.1700
Data Index: 5687356 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.9940. Min Act: -0.1700
Data Index: 6657233 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.9628. Min Act: -0.1700
Data Index: 5798752 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.9315. Min Act: -0.1700
Data Index: 7162530 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.9315. Min Act: -0.1700
Data Index: 2863848 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.9003. Min Act: -0.1700
Data Index: 2781416 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.9003. Min Act: -0.1700
Data Index: 3897143 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.9003. Min Act: -0.1700
Data Index: 8771624 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.9003. Min Act: -0.1700
Data Index: 4479984 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7402022 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8690. Min Act: -0.1700
Data Index: 799403 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8690. Min Act: -0.1700
Data Index: 4681148 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8690. Min Act: -0.1700
Data Index: 915495 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8690. Min Act: -0.1700
Data Index: 177614 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8378. Min Act: -0.1700
Data Index: 6909507 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8378. Min Act: -0.1700
Data Index: 5586798 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8378. Min Act: -0.1700
Data Index: 8668109 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8378. Min Act: -0.1700
Data Index: 7329985 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2440. Min Range: -5.2440
Max Act: 4.8378. Min Act: -0.1700
Data Index: 140926 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19