Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.8231. Min Act: -0.1700
Data Index: 4591415 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.7293. Min Act: -0.1700
Data Index: 7704654 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.6356. Min Act: -0.1700
Data Index: 4111900 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.6356. Min Act: -0.1700
Data Index: 2579626 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.6356. Min Act: -0.1700
Data Index: 7217299 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.5106. Min Act: -0.1700
Data Index: 8774752 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.4793. Min Act: -0.1700
Data Index: 3231735 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.5106. Min Act: -0.1700
Data Index: 8150810 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.5106. Min Act: -0.1700
Data Index: 6043375 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.5106. Min Act: -0.1700
Data Index: 700705 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.5106. Min Act: -0.1700
Data Index: 338492 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.5106. Min Act: -0.1700
Data Index: 2148257 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.4793. Min Act: -0.1700
Data Index: 6043376 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.4481. Min Act: -0.1700
Data Index: 8781357 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.4481. Min Act: -0.1700
Data Index: 7442891 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.4481. Min Act: -0.1700
Data Index: 700704 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.4168. Min Act: -0.1700
Data Index: 8774751 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.3856. Min Act: -0.1700
Data Index: 2860352 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.3856. Min Act: -0.1700
Data Index: 6626312 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8231. Min Range: -5.8231
Max Act: 5.3856. Min Act: -0.1700
Data Index: 2860354 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19