Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6077 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.3306. Min Act: -0.1700
Data Index: 7232125 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.2993. Min Act: -0.1700
Data Index: 3732532 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.2056. Min Act: -0.1700
Data Index: 3857576 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.1431. Min Act: -0.1700
Data Index: 2713006 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.0493. Min Act: -0.1700
Data Index: 210806 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.0181. Min Act: -0.1700
Data Index: 3527164 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.0181. Min Act: -0.1700
Data Index: 8800530 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.0181. Min Act: -0.1700
Data Index: 3399339 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.0181. Min Act: -0.1700
Data Index: 1160522 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3306. Min Range: -6.3306
Max Act: 6.0493. Min Act: -0.1700
Data Index: 7384247 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.9556. Min Act: -0.1700
Data Index: 8579793 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.9243. Min Act: -0.1700
Data Index: 5648359 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.9243. Min Act: -0.1700
Data Index: 5508928 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.9243. Min Act: -0.1700
Data Index: 6862346 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.9243. Min Act: -0.1700
Data Index: 1229797 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.9243. Min Act: -0.1700
Data Index: 5367639 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.9243. Min Act: -0.1700
Data Index: 608591 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.8931. Min Act: -0.1700
Data Index: 4901344 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.8931. Min Act: -0.1700
Data Index: 622876 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3306. Min Range: -6.3306
Max Act: 5.8931. Min Act: -0.1700
Data Index: 3282145 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19