Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 212 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5731. Min Range: -9.5731
Max Act: 9.5731. Min Act: -0.1700
Data Index: 3990269 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5731. Min Range: -9.5731
Max Act: 9.5106. Min Act: -0.1700
Data Index: 355205 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5731. Min Range: -9.5731
Max Act: 9.4481. Min Act: -0.1700
Data Index: 5670196 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5731. Min Range: -9.5731
Max Act: 9.3231. Min Act: -0.1700
Data Index: 2943758 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5731. Min Range: -9.5731
Max Act: 9.3231. Min Act: -0.1700
Data Index: 8044481 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.8856. Min Act: -0.1700
Data Index: 1573813 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.8856. Min Act: -0.1700
Data Index: 3240058 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.8856. Min Act: -0.1700
Data Index: 304202 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.8231. Min Act: -0.1700
Data Index: 2623553 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.8231. Min Act: -0.1700
Data Index: 6841538 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.8231. Min Act: -0.1700
Data Index: 5154530 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.7606. Min Act: -0.1700
Data Index: 12794 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.7606. Min Act: -0.1700
Data Index: 4475848 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.7606. Min Act: -0.1700
Data Index: 7401247 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.7606. Min Act: -0.1700
Data Index: 2525379 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.7606. Min Act: -0.1700
Data Index: 6349861 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.7606. Min Act: -0.1700
Data Index: 6684866 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.6981. Min Act: -0.1700
Data Index: 6000481 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.6981. Min Act: -0.1700
Data Index: 4496250 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5731. Min Range: -9.5731
Max Act: 8.6981. Min Act: -0.1700
Data Index: 3938318 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19