Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1484 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.6642. Min Act: -0.1700
Data Index: 467203 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.6017. Min Act: -0.1700
Data Index: 597061 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.5392. Min Act: -0.1700
Data Index: 3446963 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.3517. Min Act: -0.1700
Data Index: 1431197 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.3830. Min Act: -0.1700
Data Index: 849051 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.2580. Min Act: -0.1700
Data Index: 7765338 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.2580. Min Act: -0.1700
Data Index: 5518546 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.2267. Min Act: -0.1700
Data Index: 5469056 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.2267. Min Act: -0.1700
Data Index: 1217014 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.2267. Min Act: -0.1700
Data Index: 4975835 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1955. Min Act: -0.1700
Data Index: 7585510 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1955. Min Act: -0.1700
Data Index: 6214932 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1642. Min Act: -0.1700
Data Index: 711012 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1642. Min Act: -0.1700
Data Index: 7353084 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1330. Min Act: -0.1700
Data Index: 532824 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1330. Min Act: -0.1700
Data Index: 6915111 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1330. Min Act: -0.1700
Data Index: 5206883 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1330. Min Act: -0.1700
Data Index: 817081 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1330. Min Act: -0.1700
Data Index: 1474904 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6642. Min Range: -5.6642
Max Act: 5.1017. Min Act: -0.1700
Data Index: 2584007 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19