Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2661. Min Range: -6.2661
Max Act: 6.2661. Min Act: -0.1700
Data Index: 1609245 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.9224. Min Act: -0.1700
Data Index: 7921880 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.8911. Min Act: -0.1700
Data Index: 2733604 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.8911. Min Act: -0.1700
Data Index: 8471687 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.8599. Min Act: -0.1700
Data Index: 5859940 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.8599. Min Act: -0.1700
Data Index: 2016560 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7974. Min Act: -0.1700
Data Index: 6690476 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7661. Min Act: -0.1700
Data Index: 6783906 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4670454 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7349. Min Act: -0.1700
Data Index: 4188422 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7349. Min Act: -0.1700
Data Index: 2142072 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7349. Min Act: -0.1700
Data Index: 3937574 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7036. Min Act: -0.1700
Data Index: 1300991 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7349. Min Act: -0.1700
Data Index: 4700110 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.7349. Min Act: -0.1700
Data Index: 4431547 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.6724. Min Act: -0.1700
Data Index: 8786729 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.6724. Min Act: -0.1700
Data Index: 2601739 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.6724. Min Act: -0.1700
Data Index: 287902 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.6724. Min Act: -0.1700
Data Index: 1310901 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2661. Min Range: -6.2661
Max Act: 5.6724. Min Act: -0.1700
Data Index: 8047362 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19