Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2135 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7176. Min Range: -12.7176
Max Act: 12.7176. Min Act: -0.1700
Data Index: 7515115 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7176. Min Range: -12.7176
Max Act: 12.4051. Min Act: -0.1700
Data Index: 6270507 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7176. Min Range: -12.7176
Max Act: 12.1551. Min Act: -0.1700
Data Index: 6348307 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.7801. Min Act: -0.1700
Data Index: 6514156 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.5926. Min Act: -0.1700
Data Index: 3523158 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.5301. Min Act: -0.1700
Data Index: 7500854 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.4676. Min Act: -0.1700
Data Index: 7953185 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.4051. Min Act: -0.1700
Data Index: 8393331 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.4051. Min Act: -0.1700
Data Index: 2608081 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.4051. Min Act: -0.1700
Data Index: 6520371 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.4051. Min Act: -0.1700
Data Index: 6176359 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.4051. Min Act: -0.1700
Data Index: 3981980 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.3426. Min Act: -0.1700
Data Index: 7515116 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.3426. Min Act: -0.1700
Data Index: 5500887 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.3426. Min Act: -0.1700
Data Index: 8770990 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.2801. Min Act: -0.1700
Data Index: 2677501 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.3426. Min Act: -0.1700
Data Index: 8244108 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.2176. Min Act: -0.1700
Data Index: 2884534 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.2801. Min Act: -0.1700
Data Index: 6998380 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7176. Min Range: -12.7176
Max Act: 11.2801. Min Act: -0.1700
Data Index: 6650284 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19