Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4260 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3817. Min Range: -6.3817
Max Act: 6.3817. Min Act: -0.1700
Data Index: 7881512 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3817. Min Range: -6.3817
Max Act: 6.1942. Min Act: -0.1700
Data Index: 3543631 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3817. Min Range: -6.3817
Max Act: 6.1629. Min Act: -0.1700
Data Index: 6500300 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3817. Min Range: -6.3817
Max Act: 6.0379. Min Act: -0.1700
Data Index: 5362104 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.9754. Min Act: -0.1700
Data Index: 8789632 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.9754. Min Act: -0.1700
Data Index: 3407317 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.9442. Min Act: -0.1700
Data Index: 8091415 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.9129. Min Act: -0.1700
Data Index: 3550213 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.9129. Min Act: -0.1700
Data Index: 2384142 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8817. Min Act: -0.1700
Data Index: 2930278 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8817. Min Act: -0.1700
Data Index: 3935822 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8817. Min Act: -0.1700
Data Index: 5486166 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8817. Min Act: -0.1700
Data Index: 6296166 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8817. Min Act: -0.1700
Data Index: 27366 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8817. Min Act: -0.1700
Data Index: 5087252 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8817. Min Act: -0.1700
Data Index: 6718416 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8504. Min Act: -0.1700
Data Index: 4506993 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8504. Min Act: -0.1700
Data Index: 5584164 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8504. Min Act: -0.1700
Data Index: 3138460 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3817. Min Range: -6.3817
Max Act: 5.8192. Min Act: -0.1700
Data Index: 6547669 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19