Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.6274. Min Act: -0.1700
Data Index: 4315852 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.5337. Min Act: -0.1700
Data Index: 6796855 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.5337. Min Act: -0.1699
Data Index: 78977 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.5024. Min Act: -0.1700
Data Index: 6310239 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.5024. Min Act: -0.1700
Data Index: 7803284 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.4712. Min Act: -0.1700
Data Index: 3950780 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.3774. Min Act: -0.1700
Data Index: 6003786 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.3149. Min Act: -0.1700
Data Index: 7551148 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.2837. Min Act: -0.1700
Data Index: 3292179 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.2837. Min Act: -0.1700
Data Index: 5885219 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.2524. Min Act: -0.1700
Data Index: 4269911 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.2212. Min Act: -0.1700
Data Index: 3909626 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.2212. Min Act: -0.1700
Data Index: 5724822 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.2212. Min Act: -0.1700
Data Index: 4395919 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.2524. Min Act: -0.1700
Data Index: 5008647 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.1899. Min Act: -0.1700
Data Index: 2071638 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.1899. Min Act: -0.1700
Data Index: 5614307 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.1587. Min Act: -0.1700
Data Index: 3108395 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.1587. Min Act: -0.1700
Data Index: 6207059 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6274. Min Range: -6.6274
Max Act: 6.1274. Min Act: -0.1700
Data Index: 4509537 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19