Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 929 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.8595. Min Act: -0.1700
Data Index: 4017671 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.5782. Min Act: -0.1700
Data Index: 1239840 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.4845. Min Act: -0.1700
Data Index: 4666631 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.4532. Min Act: -0.1700
Data Index: 6008910 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.4220. Min Act: -0.1700
Data Index: 5234431 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.3595. Min Act: -0.1700
Data Index: 8771591 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.3595. Min Act: -0.1700
Data Index: 786132 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.3282. Min Act: -0.1700
Data Index: 5295895 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.3282. Min Act: -0.1700
Data Index: 5750226 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.2970. Min Act: -0.1700
Data Index: 8488454 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.3282. Min Act: -0.1700
Data Index: 6306071 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.3282. Min Act: -0.1700
Data Index: 804637 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.3282. Min Act: -0.1700
Data Index: 1262602 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.2970. Min Act: -0.1700
Data Index: 3837801 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.2970. Min Act: -0.1700
Data Index: 617088 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.2970. Min Act: -0.1700
Data Index: 6502745 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.2970. Min Act: -0.1700
Data Index: 545397 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.2970. Min Act: -0.1700
Data Index: 6939000 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.2970. Min Act: -0.1700
Data Index: 7473065 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8595. Min Range: -4.8595
Max Act: 4.3282. Min Act: -0.1700
Data Index: 866889 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19