Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.7764. Min Act: -0.1700
Data Index: 1564927 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.7764. Min Act: -0.1700
Data Index: 3649466 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.7451. Min Act: -0.1700
Data Index: 2296088 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.6201. Min Act: -0.1700
Data Index: 5346053 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.6201. Min Act: -0.1700
Data Index: 274259 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.5576. Min Act: -0.1700
Data Index: 3864297 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.5264. Min Act: -0.1700
Data Index: 7537538 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.4951. Min Act: -0.1700
Data Index: 4484966 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.4639. Min Act: -0.1700
Data Index: 1356691 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.4326. Min Act: -0.1700
Data Index: 2746216 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.4014. Min Act: -0.1700
Data Index: 3916975 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.3389. Min Act: -0.1700
Data Index: 3728797 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.3076. Min Act: -0.1700
Data Index: 4763100 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.2451. Min Act: -0.1700
Data Index: 8400526 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.2764. Min Act: -0.1700
Data Index: 1833681 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.2764. Min Act: -0.1700
Data Index: 4410449 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.2451. Min Act: -0.1700
Data Index: 5915392 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.2139. Min Act: -0.1700
Data Index: 7946537 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.2139. Min Act: -0.1700
Data Index: 4730847 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7764. Min Range: -6.7764
Max Act: 6.2451. Min Act: -0.1700
Data Index: 4997052 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19