Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.7919. Min Act: -0.1700
Data Index: 6978701 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.7294. Min Act: -0.1700
Data Index: 8025981 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.7606. Min Act: -0.1700
Data Index: 2399358 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6981. Min Act: -0.1700
Data Index: 2168933 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6981. Min Act: -0.1700
Data Index: 4589536 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6669. Min Act: -0.1700
Data Index: 5737487 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6669. Min Act: -0.1700
Data Index: 1707457 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6356. Min Act: -0.1700
Data Index: 5609160 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6356. Min Act: -0.1700
Data Index: 5226376 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6356. Min Act: -0.1700
Data Index: 5954944 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6044. Min Act: -0.1700
Data Index: 7032748 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6356. Min Act: -0.1700
Data Index: 6112173 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6356. Min Act: -0.1693
Data Index: 6436689 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6356. Min Act: -0.1699
Data Index: 1771380 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.5731. Min Act: -0.1700
Data Index: 5524640 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6044. Min Act: -0.1700
Data Index: 1624449 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6044. Min Act: -0.1700
Data Index: 4306143 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.5731. Min Act: -0.1700
Data Index: 732815 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.6044. Min Act: -0.1700
Data Index: 3412311 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7919. Min Range: -5.7919
Max Act: 5.5731. Min Act: -0.1700
Data Index: 6597385 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19