Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4628. Min Range: -7.4628
Max Act: 7.4628. Min Act: -0.1700
Data Index: 4545169 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4628. Min Range: -7.4628
Max Act: 7.2753. Min Act: -0.1700
Data Index: 1990937 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4628. Min Range: -7.4628
Max Act: 7.2128. Min Act: -0.1700
Data Index: 4691782 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4628. Min Range: -7.4628
Max Act: 7.1191. Min Act: -0.1700
Data Index: 2783632 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.8378. Min Act: -0.1700
Data Index: 4882191 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.8066. Min Act: -0.1700
Data Index: 3450517 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.7753. Min Act: -0.1700
Data Index: 1570911 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.6191. Min Act: -0.1700
Data Index: 7256400 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.6191. Min Act: -0.1700
Data Index: 3316433 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.6191. Min Act: -0.1700
Data Index: 3085201 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.5566. Min Act: -0.1700
Data Index: 8090231 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4941. Min Act: -0.1700
Data Index: 568855 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4628. Min Act: -0.1700
Data Index: 5534156 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4628. Min Act: -0.1700
Data Index: 3894247 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4628. Min Act: -0.1700
Data Index: 8010378 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4316. Min Act: -0.1700
Data Index: 1570906 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4316. Min Act: -0.1700
Data Index: 5765378 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4003. Min Act: -0.1700
Data Index: 6121007 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4003. Min Act: -0.1700
Data Index: 6644849 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4628. Min Range: -7.4628
Max Act: 6.4003. Min Act: -0.1700
Data Index: 506248 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19