Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5229 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1878. Min Range: -6.1878
Max Act: 6.1878. Min Act: -0.1700
Data Index: 2294345 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.7503. Min Act: -0.1700
Data Index: 1312755 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.5941. Min Act: -0.1700
Data Index: 6753386 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.4378. Min Act: -0.1700
Data Index: 8386436 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.3753. Min Act: -0.1700
Data Index: 4919692 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.3441. Min Act: -0.1700
Data Index: 7221978 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.3128. Min Act: -0.1700
Data Index: 6536221 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.3128. Min Act: -0.1700
Data Index: 6766679 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.3128. Min Act: -0.1700
Data Index: 8080552 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.3128. Min Act: -0.1700
Data Index: 8054370 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.2816. Min Act: -0.1700
Data Index: 5730826 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.2503. Min Act: -0.1700
Data Index: 5684579 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4398300 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.2191. Min Act: -0.1700
Data Index: 1676253 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4593121 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.1566. Min Act: -0.1700
Data Index: 3727562 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.1566. Min Act: -0.1700
Data Index: 8041367 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.1878. Min Act: -0.1700
Data Index: 2413776 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.1878. Min Act: -0.1700
Data Index: 2366189 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1878. Min Range: -6.1878
Max Act: 5.1878. Min Act: -0.1700
Data Index: 1544507 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19