Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1751 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1959. Min Act: -0.1700
Data Index: 4776664 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1959. Min Act: -0.1700
Data Index: 601951 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.0397. Min Act: -0.1700
Data Index: 8035017 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.9771. Min Act: -0.1700
Data Index: 6284571 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.9771. Min Act: -0.1700
Data Index: 1949803 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.9459. Min Act: -0.1700
Data Index: 7216461 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.9459. Min Act: -0.1700
Data Index: 5626944 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.9459. Min Act: -0.1700
Data Index: 1208566 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.9146. Min Act: -0.1700
Data Index: 8106787 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8833. Min Act: -0.1700
Data Index: 5706344 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.9146. Min Act: -0.1700
Data Index: 974861 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8833. Min Act: -0.1700
Data Index: 8541713 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8833. Min Act: -0.1700
Data Index: 1189927 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8833. Min Act: -0.1700
Data Index: 526772 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8833. Min Act: -0.1700
Data Index: 2892611 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8833. Min Act: -0.1700
Data Index: 1190556 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8521. Min Act: -0.1700
Data Index: 3398928 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8833. Min Act: -0.1700
Data Index: 30649 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8521. Min Act: -0.1700
Data Index: 7197773 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1959. Min Range: -4.1959
Max Act: 3.8833. Min Act: -0.1700
Data Index: 766318 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19