Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1933 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.6836. Min Act: -0.1700
Data Index: 6299782 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.6211. Min Act: -0.1700
Data Index: 5492865 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.6211. Min Act: -0.1700
Data Index: 2526365 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.5899. Min Act: -0.1700
Data Index: 3846889 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.6211. Min Act: -0.1700
Data Index: 6642754 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4961. Min Act: -0.1700
Data Index: 6255737 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4961. Min Act: -0.1700
Data Index: 8377320 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4961. Min Act: -0.1700
Data Index: 305016 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4961. Min Act: -0.1700
Data Index: 3047279 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4336. Min Act: -0.1700
Data Index: 3350667 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4961. Min Act: -0.1700
Data Index: 4449962 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4649. Min Act: -0.1700
Data Index: 4719165 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4336. Min Act: -0.1700
Data Index: 5684418 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4336. Min Act: -0.1700
Data Index: 7358720 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4336. Min Act: -0.1700
Data Index: 2515135 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4649. Min Act: -0.1700
Data Index: 891306 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4024. Min Act: -0.1700
Data Index: 659770 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4024. Min Act: -0.1700
Data Index: 595438 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.3711. Min Act: -0.1700
Data Index: 3173989 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6836. Min Range: -6.6836
Max Act: 6.4336. Min Act: -0.1700
Data Index: 7198887 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19