Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4526 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.9872. Min Act: -0.1700
Data Index: 254248 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.6122. Min Act: -0.1700
Data Index: 2012129 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.2997. Min Act: -0.1700
Data Index: 1824265 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.2997. Min Act: -0.1700
Data Index: 5616081 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.2372. Min Act: -0.1700
Data Index: 3468463 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.2372. Min Act: -0.1700
Data Index: 2368947 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.2372. Min Act: -0.1700
Data Index: 727143 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.1747. Min Act: -0.1700
Data Index: 587223 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.1747. Min Act: -0.1700
Data Index: 6741260 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.1747. Min Act: -0.1700
Data Index: 5608875 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.1747. Min Act: -0.1700
Data Index: 5207466 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.1122. Min Act: -0.1700
Data Index: 5500604 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.1122. Min Act: -0.1700
Data Index: 2146380 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.0497. Min Act: -0.1699
Data Index: 4324129 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.0497. Min Act: -0.1700
Data Index: 8226252 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.0497. Min Act: -0.1700
Data Index: 6753338 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9872. Min Range: -10.9872
Max Act: 10.0497. Min Act: -0.1700
Data Index: 3044474 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9872. Min Range: -10.9872
Max Act: 9.9247. Min Act: -0.1700
Data Index: 6030184 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9872. Min Range: -10.9872
Max Act: 9.9872. Min Act: -0.1700
Data Index: 5792513 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9872. Min Range: -10.9872
Max Act: 9.9247. Min Act: -0.1700
Data Index: 2225213 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19