Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1630 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.9271. Min Act: -0.1700
Data Index: 4918947 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.8959. Min Act: -0.1700
Data Index: 7071855 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.8334. Min Act: -0.1700
Data Index: 3159891 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.7084. Min Act: -0.1700
Data Index: 7414159 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.7084. Min Act: -0.1700
Data Index: 3143841 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.7084. Min Act: -0.1700
Data Index: 693864 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.7084. Min Act: -0.1700
Data Index: 6722955 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.6459. Min Act: -0.1700
Data Index: 1582871 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.6459. Min Act: -0.1700
Data Index: 3406222 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.6771. Min Act: -0.1700
Data Index: 6109236 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.5834. Min Act: -0.1700
Data Index: 3406225 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.5834. Min Act: -0.1700
Data Index: 1522491 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.5209. Min Act: -0.1700
Data Index: 4016207 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.4896. Min Act: -0.1700
Data Index: 693870 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.4271. Min Act: -0.1700
Data Index: 5339536 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.4271. Min Act: -0.1700
Data Index: 455875 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.3959. Min Act: -0.1700
Data Index: 3520916 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.3646. Min Act: -0.1700
Data Index: 7192236 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.3646. Min Act: -0.1700
Data Index: 3786761 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9271. Min Range: -6.9271
Max Act: 6.3334. Min Act: -0.1700
Data Index: 3686675 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19