Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5158 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.3777. Min Act: -0.1700
Data Index: 7587164 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.3465. Min Act: -0.1700
Data Index: 7623127 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.3152. Min Act: -0.1700
Data Index: 1218685 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.2214. Min Act: -0.1700
Data Index: 4475653 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.1902. Min Act: -0.1700
Data Index: 191187 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.1589. Min Act: -0.1700
Data Index: 5377771 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.1277. Min Act: -0.1700
Data Index: 4176587 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.1277. Min Act: -0.1700
Data Index: 3686378 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0964. Min Act: -0.1700
Data Index: 6030763 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0964. Min Act: -0.1700
Data Index: 3315014 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0964. Min Act: -0.1700
Data Index: 4982327 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0964. Min Act: -0.1700
Data Index: 3850780 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0652. Min Act: -0.1700
Data Index: 591220 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0652. Min Act: -0.1700
Data Index: 6758912 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0964. Min Act: -0.1700
Data Index: 2543217 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0652. Min Act: -0.1700
Data Index: 1200317 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0339. Min Act: -0.1700
Data Index: 6949766 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0339. Min Act: -0.1700
Data Index: 926388 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0652. Min Act: -0.1700
Data Index: 3329406 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3777. Min Range: -4.3777
Max Act: 4.0339. Min Act: -0.1700
Data Index: 3351424 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19