Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.5481. Min Act: -0.1700
Data Index: 1229974 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.2668. Min Act: -0.1700
Data Index: 2362569 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.2043. Min Act: -0.1700
Data Index: 2796145 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.2043. Min Act: -0.1700
Data Index: 6213111 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1418. Min Act: -0.1700
Data Index: 152385 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1731. Min Act: -0.1700
Data Index: 3653858 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1731. Min Act: -0.1700
Data Index: 98450 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1731. Min Act: -0.1700
Data Index: 4954725 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1731. Min Act: -0.1700
Data Index: 3565958 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1418. Min Act: -0.1700
Data Index: 1042807 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1418. Min Act: -0.1700
Data Index: 7813258 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1106. Min Act: -0.1700
Data Index: 6378996 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1106. Min Act: -0.1700
Data Index: 1954161 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1106. Min Act: -0.1700
Data Index: 6319726 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1106. Min Act: -0.1700
Data Index: 4455505 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.1106. Min Act: -0.1700
Data Index: 8052575 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.0793. Min Act: -0.1700
Data Index: 5955561 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.0793. Min Act: -0.1700
Data Index: 4512137 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.0793. Min Act: -0.1700
Data Index: 2496750 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5481. Min Range: -5.5481
Max Act: 5.0793. Min Act: -0.1700
Data Index: 5283415 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19