Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5172. Min Range: -6.5172
Max Act: 6.5172. Min Act: -0.1700
Data Index: 3854473 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5172. Min Range: -6.5172
Max Act: 6.2672. Min Act: -0.1700
Data Index: 3436551 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5172. Min Range: -6.5172
Max Act: 6.2360. Min Act: -0.1700
Data Index: 555197 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5172. Min Range: -6.5172
Max Act: 6.0485. Min Act: -0.1700
Data Index: 7163928 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5172. Min Range: -6.5172
Max Act: 6.0485. Min Act: -0.1700
Data Index: 530980 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5172. Min Range: -6.5172
Max Act: 6.0172. Min Act: -0.1700
Data Index: 3485840 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9860. Min Act: -0.1700
Data Index: 1111480 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9547. Min Act: -0.1700
Data Index: 573141 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 248755 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 56048 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 5366425 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 7243705 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 6940860 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 1494095 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.8922. Min Act: -0.1700
Data Index: 2008685 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 2365002 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.8922. Min Act: -0.1700
Data Index: 2166825 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 5498694 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.9235. Min Act: -0.1700
Data Index: 1882974 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5172. Min Range: -6.5172
Max Act: 5.8922. Min Act: -0.1700
Data Index: 6463952 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19