Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.9533. Min Act: -0.1700
Data Index: 2812964 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.5466. Min Act: -0.1700
Data Index: 8166997 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.4056. Min Act: -0.1700
Data Index: 7222239 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.4056. Min Act: -0.1700
Data Index: 4341261 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3743. Min Act: -0.1700
Data Index: 7729300 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3586. Min Act: -0.1700
Data Index: 1775887 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3586. Min Act: -0.1700
Data Index: 3339920 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3429. Min Act: -0.1700
Data Index: 8083567 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3429. Min Act: -0.1700
Data Index: 884948 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3272. Min Act: -0.1700
Data Index: 3505070 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3272. Min Act: -0.1700
Data Index: 4052010 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3115. Min Act: -0.1700
Data Index: 1901213 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3272. Min Act: -0.1700
Data Index: 7118806 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3115. Min Act: -0.1700
Data Index: 8760 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.2958. Min Act: -0.1700
Data Index: 7361563 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.3115. Min Act: -0.1700
Data Index: 128705 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.2958. Min Act: -0.1700
Data Index: 1329417 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.2801. Min Act: -0.1700
Data Index: 4759991 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.2644. Min Act: -0.1700
Data Index: 3185125 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9533. Min Range: -3.9533
Max Act: 3.2644. Min Act: -0.1700
Data Index: 28806 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19