Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0986. Min Range: -8.0986
Max Act: 8.0986. Min Act: -0.1700
Data Index: 7634673 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0986. Min Range: -8.0986
Max Act: 8.0673. Min Act: -0.1700
Data Index: 5785396 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0986. Min Range: -8.0986
Max Act: 8.0361. Min Act: -0.1700
Data Index: 3570409 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.9423. Min Act: -0.1700
Data Index: 2732042 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.9423. Min Act: -0.1700
Data Index: 3540230 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.8173. Min Act: -0.1700
Data Index: 3425507 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.6923. Min Act: -0.1700
Data Index: 5132937 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.6611. Min Act: -0.1700
Data Index: 4215276 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.5361. Min Act: -0.1700
Data Index: 359303 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.5361. Min Act: -0.1700
Data Index: 8030449 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.4111. Min Act: -0.1700
Data Index: 8394720 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.4423. Min Act: -0.1700
Data Index: 6705307 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.4736. Min Act: -0.1700
Data Index: 2903710 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.4423. Min Act: -0.1700
Data Index: 4674751 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.4111. Min Act: -0.1700
Data Index: 1462691 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.4111. Min Act: -0.1700
Data Index: 5209183 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.3798. Min Act: -0.1700
Data Index: 2548855 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.3798. Min Act: -0.1700
Data Index: 734622 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.3486. Min Act: -0.1700
Data Index: 4480317 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0986. Min Range: -8.0986
Max Act: 7.3486. Min Act: -0.1700
Data Index: 603802 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19