Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4141 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.7917. Min Act: -0.1700
Data Index: 8557298 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.6667. Min Act: -0.1700
Data Index: 7979440 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.6042. Min Act: -0.1700
Data Index: 7979438 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.2604. Min Act: -0.1700
Data Index: 4542803 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.2292. Min Act: -0.1700
Data Index: 2055789 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1979. Min Act: -0.1700
Data Index: 141724 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1979. Min Act: -0.1700
Data Index: 4698405 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1667. Min Act: -0.1700
Data Index: 1585955 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1667. Min Act: -0.1700
Data Index: 6609999 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1354. Min Act: -0.1700
Data Index: 2541072 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1354. Min Act: -0.1700
Data Index: 5060130 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1354. Min Act: -0.1700
Data Index: 1681611 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1042. Min Act: -0.1700
Data Index: 3854517 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1042. Min Act: -0.1700
Data Index: 3283463 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.1042. Min Act: -0.1700
Data Index: 5497600 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.0729. Min Act: -0.1700
Data Index: 3866368 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.0729. Min Act: -0.1700
Data Index: 2129835 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.0417. Min Act: -0.1700
Data Index: 5627783 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.0417. Min Act: -0.1700
Data Index: 958215 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7917. Min Range: -5.7917
Max Act: 5.0104. Min Act: -0.1700
Data Index: 4081116 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19