Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4659 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.4086. Min Act: -0.1700
Data Index: 1670411 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.4086. Min Act: -0.1700
Data Index: 8529238 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.3148. Min Act: -0.1700
Data Index: 8788472 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1898. Min Act: -0.1700
Data Index: 1300733 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.2211. Min Act: -0.1700
Data Index: 8135260 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.2211. Min Act: -0.1700
Data Index: 4872685 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.2211. Min Act: -0.1700
Data Index: 4484610 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1898. Min Act: -0.1700
Data Index: 8574503 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1898. Min Act: -0.1700
Data Index: 3186694 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1898. Min Act: -0.1700
Data Index: 7449425 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1586. Min Act: -0.1700
Data Index: 3331177 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1586. Min Act: -0.1700
Data Index: 8270884 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1273. Min Act: -0.1700
Data Index: 3029593 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1586. Min Act: -0.1700
Data Index: 8037060 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1586. Min Act: -0.1700
Data Index: 2328968 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1586. Min Act: -0.1700
Data Index: 2328971 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1586. Min Act: -0.1700
Data Index: 2791746 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1273. Min Act: -0.1700
Data Index: 5472756 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1273. Min Act: -0.1700
Data Index: 6216824 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4086. Min Range: -5.4086
Max Act: 5.1273. Min Act: -0.1700
Data Index: 6500070 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19