Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0899. Min Range: -6.0899
Max Act: 6.0899. Min Act: -0.1700
Data Index: 6320476 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.9962. Min Act: -0.1700
Data Index: 6320481 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.8712. Min Act: -0.1700
Data Index: 7995104 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.8712. Min Act: -0.1700
Data Index: 2410994 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.8399. Min Act: -0.1700
Data Index: 2410999 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.8712. Min Act: -0.1700
Data Index: 8210382 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.8399. Min Act: -0.1700
Data Index: 7995105 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.8087. Min Act: -0.1700
Data Index: 4441682 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7774. Min Act: -0.1700
Data Index: 680603 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7774. Min Act: -0.1700
Data Index: 3127833 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7774. Min Act: -0.1700
Data Index: 380463 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7774. Min Act: -0.1700
Data Index: 1902904 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7774. Min Act: -0.1700
Data Index: 3372097 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7462. Min Act: -0.1700
Data Index: 5205111 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7462. Min Act: -0.1700
Data Index: 1927337 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7462. Min Act: -0.1700
Data Index: 3340034 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7149. Min Act: -0.1700
Data Index: 2460427 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7149. Min Act: -0.1700
Data Index: 3127841 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7149. Min Act: -0.1700
Data Index: 6320482 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0899. Min Range: -6.0899
Max Act: 5.7149. Min Act: -0.1700
Data Index: 5158146 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19