Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4854. Min Act: -0.1700
Data Index: 6312837 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3604. Min Act: -0.1700
Data Index: 6312836 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3292. Min Act: -0.1700
Data Index: 280512 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.2979. Min Act: -0.1700
Data Index: 8123547 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.2667. Min Act: -0.1700
Data Index: 7963414 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.2979. Min Act: -0.1700
Data Index: 4529227 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.2042. Min Act: -0.1700
Data Index: 1167200 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.1416. Min Act: -0.1700
Data Index: 5694237 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.1729. Min Act: -0.1700
Data Index: 2444897 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.1729. Min Act: -0.1700
Data Index: 598057 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.1729. Min Act: -0.1700
Data Index: 4593648 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.1729. Min Act: -0.1700
Data Index: 3139997 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.1729. Min Act: -0.1700
Data Index: 5478706 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.1416. Min Act: -0.1700
Data Index: 8730810 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.0791. Min Act: -0.1700
Data Index: 4365435 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.0791. Min Act: -0.1700
Data Index: 432557 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.0791. Min Act: -0.1700
Data Index: 4106185 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.0166. Min Act: -0.1700
Data Index: 6969538 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.0166. Min Act: -0.1700
Data Index: 726722 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.0479. Min Act: -0.1700
Data Index: 5240639 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19