Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.5035. Min Act: -0.1700
Data Index: 252142 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.4410. Min Act: -0.1700
Data Index: 252145 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.3472. Min Act: -0.1700
Data Index: 252151 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.2222. Min Act: -0.1700
Data Index: 4779534 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.2222. Min Act: -0.1700
Data Index: 252148 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.1597. Min Act: -0.1700
Data Index: 252144 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.1597. Min Act: -0.1700
Data Index: 252140 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.1285. Min Act: -0.1700
Data Index: 5584776 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.1597. Min Act: -0.1700
Data Index: 252146 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.1285. Min Act: -0.1699
Data Index: 252149 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0972. Min Act: -0.1700
Data Index: 7837441 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0972. Min Act: -0.1700
Data Index: 5584775 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0972. Min Act: -0.1700
Data Index: 5584777 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0660. Min Act: -0.1700
Data Index: 5584779 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0347. Min Act: -0.1700
Data Index: 6735771 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0035. Min Act: -0.1700
Data Index: 5584774 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5035. Min Range: -7.5035
Max Act: 7.0035. Min Act: -0.1700
Data Index: 7177812 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.9410. Min Act: -0.1700
Data Index: 4488040 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.9097. Min Act: -0.1700
Data Index: 6703398 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5035. Min Range: -7.5035
Max Act: 6.9097. Min Act: -0.1700
Data Index: 6022286 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19