Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5996. Min Range: -6.5996
Max Act: 6.5996. Min Act: -0.1700
Data Index: 2316286 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5996. Min Range: -6.5996
Max Act: 6.2558. Min Act: -0.1700
Data Index: 7657931 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5996. Min Range: -6.5996
Max Act: 6.2246. Min Act: -0.1700
Data Index: 3397576 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5996. Min Range: -6.5996
Max Act: 6.2246. Min Act: -0.1700
Data Index: 6846861 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5996. Min Range: -6.5996
Max Act: 6.1621. Min Act: -0.1700
Data Index: 760481 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5996. Min Range: -6.5996
Max Act: 6.1308. Min Act: -0.1700
Data Index: 8161332 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5996. Min Range: -6.5996
Max Act: 6.0371. Min Act: -0.1700
Data Index: 2005391 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.9746. Min Act: -0.1700
Data Index: 4832082 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5996. Min Range: -6.5996
Max Act: 6.0058. Min Act: -0.1700
Data Index: 1262776 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.9746. Min Act: -0.1700
Data Index: 842046 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.9746. Min Act: -0.1700
Data Index: 2822083 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.9746. Min Act: -0.1700
Data Index: 7074167 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.9433. Min Act: -0.1700
Data Index: 407747 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.9121. Min Act: -0.1700
Data Index: 600514 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.9121. Min Act: -0.1700
Data Index: 238379 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.8808. Min Act: -0.1700
Data Index: 5537441 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.8496. Min Act: -0.1700
Data Index: 6335398 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.8183. Min Act: -0.1700
Data Index: 4678136 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.8808. Min Act: -0.1700
Data Index: 3970434 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5996. Min Range: -6.5996
Max Act: 5.8496. Min Act: -0.1700
Data Index: 516251 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19