Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5091 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.9927. Min Act: -0.1700
Data Index: 8405268 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.6490. Min Act: -0.1700
Data Index: 13106 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.6490. Min Act: -0.1700
Data Index: 3141802 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.6490. Min Act: -0.1700
Data Index: 3775028 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.5865. Min Act: -0.1700
Data Index: 5418651 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.5552. Min Act: -0.1700
Data Index: 2936251 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.5552. Min Act: -0.1700
Data Index: 8864 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.5240. Min Act: -0.1700
Data Index: 6134858 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.5240. Min Act: -0.1700
Data Index: 7773686 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4615. Min Act: -0.1700
Data Index: 1135711 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4615. Min Act: -0.1700
Data Index: 1829902 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4615. Min Act: -0.1700
Data Index: 6287050 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4615. Min Act: -0.1700
Data Index: 628431 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4615. Min Act: -0.1700
Data Index: 7325959 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4615. Min Act: -0.1700
Data Index: 45501 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4302. Min Act: -0.1700
Data Index: 7773685 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4302. Min Act: -0.1700
Data Index: 4381230 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.4302. Min Act: -0.1700
Data Index: 4433679 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.3990. Min Act: -0.1700
Data Index: 1013106 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9927. Min Range: -5.9927
Max Act: 5.3990. Min Act: -0.1700
Data Index: 1616008 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19