Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4417 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.7551. Min Act: -0.1700
Data Index: 5478521 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.7238. Min Act: -0.1700
Data Index: 7401085 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6925. Min Act: -0.1700
Data Index: 5852138 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6299. Min Act: -0.1700
Data Index: 2672944 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6299. Min Act: -0.1700
Data Index: 7421895 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5986. Min Act: -0.1700
Data Index: 6057313 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.6299. Min Act: -0.1700
Data Index: 6386260 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5986. Min Act: -0.1700
Data Index: 3224181 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5360. Min Act: -0.1700
Data Index: 5406199 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5673. Min Act: -0.1697
Data Index: 1022152 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5673. Min Act: -0.1700
Data Index: 1783 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5047. Min Act: -0.1700
Data Index: 3631557 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5047. Min Act: -0.1700
Data Index: 2111177 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5047. Min Act: -0.1700
Data Index: 1886048 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5047. Min Act: -0.1700
Data Index: 1168636 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5047. Min Act: -0.1700
Data Index: 663257 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5047. Min Act: -0.1700
Data Index: 135308 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5047. Min Act: -0.1700
Data Index: 4978575 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.4733. Min Act: -0.1700
Data Index: 2206066 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7551. Min Range: -3.7551
Max Act: 3.5360. Min Act: -0.1700
Data Index: 3816186 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19