Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1896 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.3112. Min Act: -0.1700
Data Index: 4199656 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.2487. Min Act: -0.1700
Data Index: 4256615 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.2175. Min Act: -0.1700
Data Index: 7422858 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.1862. Min Act: -0.1700
Data Index: 2587879 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.0925. Min Act: -0.1700
Data Index: 738058 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.0925. Min Act: -0.1700
Data Index: 5503271 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.0925. Min Act: -0.1700
Data Index: 5868214 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.0612. Min Act: -0.1700
Data Index: 5581803 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.9987. Min Act: -0.1700
Data Index: 3067978 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.0300. Min Act: -0.1700
Data Index: 8004024 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.9987. Min Act: -0.1700
Data Index: 6350832 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3112. Min Range: -6.3112
Max Act: 6.0300. Min Act: -0.1700
Data Index: 2462979 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.9675. Min Act: -0.1700
Data Index: 681725 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.9987. Min Act: -0.1700
Data Index: 1040186 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.9987. Min Act: -0.1700
Data Index: 2450880 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.9362. Min Act: -0.1700
Data Index: 6641185 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.9050. Min Act: -0.1700
Data Index: 5910310 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.9050. Min Act: -0.1700
Data Index: 762426 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.8737. Min Act: -0.1700
Data Index: 182336 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3112. Min Range: -6.3112
Max Act: 5.8737. Min Act: -0.1700
Data Index: 7035666 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19