Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6339 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.7294. Min Act: -0.1700
Data Index: 3591282 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.6981. Min Act: -0.1700
Data Index: 2286001 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.6356. Min Act: -0.1700
Data Index: 5347247 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.6044. Min Act: -0.1700
Data Index: 2881693 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.5419. Min Act: -0.1700
Data Index: 7472520 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.5419. Min Act: -0.1700
Data Index: 5347246 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.5106. Min Act: -0.1700
Data Index: 4996552 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.5106. Min Act: -0.1700
Data Index: 5796026 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.4794. Min Act: -0.1700
Data Index: 5347248 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.4794. Min Act: -0.1700
Data Index: 119776 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.4794. Min Act: -0.1700
Data Index: 6022354 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.4794. Min Act: -0.1700
Data Index: 4036308 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.4481. Min Act: -0.1700
Data Index: 7139536 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.4481. Min Act: -0.1700
Data Index: 6022600 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.3856. Min Act: -0.1700
Data Index: 5151765 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.3856. Min Act: -0.1700
Data Index: 4954495 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.3856. Min Act: -0.1700
Data Index: 8204948 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.3544. Min Act: -0.1700
Data Index: 4203029 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.3544. Min Act: -0.1700
Data Index: 1984617 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7294. Min Range: -5.7294
Max Act: 5.3231. Min Act: -0.1700
Data Index: 4309072 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19