Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2466 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0359. Min Range: -6.0359
Max Act: 6.0359. Min Act: -0.1700
Data Index: 6826088 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0359. Min Range: -6.0359
Max Act: 6.0047. Min Act: -0.1700
Data Index: 2974978 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0359. Min Range: -6.0359
Max Act: 6.0047. Min Act: -0.1700
Data Index: 901242 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.9109. Min Act: -0.1700
Data Index: 2091093 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.9109. Min Act: -0.1700
Data Index: 5296726 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.8797. Min Act: -0.1700
Data Index: 7978161 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.8484. Min Act: -0.1700
Data Index: 3851704 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.7859. Min Act: -0.1700
Data Index: 8538793 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.8172. Min Act: -0.1700
Data Index: 739230 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.8172. Min Act: -0.1700
Data Index: 4551194 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.7859. Min Act: -0.1700
Data Index: 3517257 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.7859. Min Act: -0.1700
Data Index: 6271505 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.7547. Min Act: -0.1700
Data Index: 5743190 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.7859. Min Act: -0.1700
Data Index: 7969733 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.7234. Min Act: -0.1700
Data Index: 2204318 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.7234. Min Act: -0.1700
Data Index: 620856 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.6922. Min Act: -0.1700
Data Index: 2727066 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.7234. Min Act: -0.1700
Data Index: 6678955 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.6922. Min Act: -0.1700
Data Index: 5780960 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0359. Min Range: -6.0359
Max Act: 5.6609. Min Act: -0.1700
Data Index: 1190188 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19