Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0933. Min Range: -8.0933
Max Act: 8.0933. Min Act: -0.1700
Data Index: 5440327 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.7183. Min Act: -0.1700
Data Index: 5678355 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.6246. Min Act: -0.1700
Data Index: 6864621 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.5933. Min Act: -0.1700
Data Index: 4280676 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.3121. Min Act: -0.1700
Data Index: 2208476 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.2808. Min Act: -0.1700
Data Index: 521781 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.2183. Min Act: -0.1700
Data Index: 8127252 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.1871. Min Act: -0.1700
Data Index: 2190217 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.1558. Min Act: -0.1700
Data Index: 2980552 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.1558. Min Act: -0.1700
Data Index: 4222320 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.1246. Min Act: -0.1700
Data Index: 4200626 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.1558. Min Act: -0.1700
Data Index: 8586408 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.1246. Min Act: -0.1700
Data Index: 4226088 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.0933. Min Act: -0.1700
Data Index: 4049299 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.0621. Min Act: -0.1700
Data Index: 5477786 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0933. Min Range: -8.0933
Max Act: 6.9996. Min Act: -0.1700
Data Index: 3197654 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0933. Min Range: -8.0933
Max Act: 7.0308. Min Act: -0.1700
Data Index: 6374838 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0933. Min Range: -8.0933
Max Act: 6.9996. Min Act: -0.1700
Data Index: 1987291 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0933. Min Range: -8.0933
Max Act: 6.9996. Min Act: -0.1700
Data Index: 628585 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0933. Min Range: -8.0933
Max Act: 6.9996. Min Act: -0.1700
Data Index: 2907023 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19