Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4815 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2667. Min Range: -11.2667
Max Act: 11.2667. Min Act: -0.1700
Data Index: 7239012 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.9542. Min Act: -0.1700
Data Index: 6187146 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.8917. Min Act: -0.1700
Data Index: 919965 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.7667. Min Act: -0.1700
Data Index: 2578700 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.7667. Min Act: -0.1700
Data Index: 5338147 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.6417. Min Act: -0.1700
Data Index: 2362567 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.7042. Min Act: -0.1700
Data Index: 607839 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.7042. Min Act: -0.1700
Data Index: 4591580 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.6417. Min Act: -0.1700
Data Index: 2370901 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.6417. Min Act: -0.1700
Data Index: 532692 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.6417. Min Act: -0.1700
Data Index: 2808747 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.6417. Min Act: -0.1700
Data Index: 4783568 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.6417. Min Act: -0.1700
Data Index: 6187147 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.5792. Min Act: -0.1700
Data Index: 4934059 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.5167. Min Act: -0.1700
Data Index: 6471433 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.5792. Min Act: -0.1700
Data Index: 7990188 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.5792. Min Act: -0.1700
Data Index: 3382299 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.5792. Min Act: -0.1700
Data Index: 7822917 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.6417. Min Act: -0.1700
Data Index: 7239013 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2667. Min Range: -11.2667
Max Act: 10.4542. Min Act: -0.1700
Data Index: 2905565 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19