Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 151 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.9108. Min Act: -0.1700
Data Index: 1538698 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.6920. Min Act: -0.1700
Data Index: 4409486 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.6295. Min Act: -0.1700
Data Index: 4146937 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.5983. Min Act: -0.1700
Data Index: 1177560 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.5670. Min Act: -0.1700
Data Index: 3092836 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.5670. Min Act: -0.1700
Data Index: 2224967 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.5358. Min Act: -0.1700
Data Index: 3863941 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.5358. Min Act: -0.1700
Data Index: 6737266 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.5045. Min Act: -0.1700
Data Index: 437881 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.5045. Min Act: -0.1700
Data Index: 4569423 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4733. Min Act: -0.1700
Data Index: 2335057 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4733. Min Act: -0.1700
Data Index: 5635858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4420. Min Act: -0.1700
Data Index: 4760068 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4420. Min Act: -0.1700
Data Index: 6863073 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4420. Min Act: -0.1700
Data Index: 7576708 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4108. Min Act: -0.1700
Data Index: 2560090 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.4108. Min Act: -0.1700
Data Index: 1724292 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.3795. Min Act: -0.1700
Data Index: 3530080 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.3795. Min Act: -0.1700
Data Index: 4628634 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9108. Min Range: -6.9108
Max Act: 6.3483. Min Act: -0.1700
Data Index: 4051444 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19