Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.5678. Min Act: -0.1700
Data Index: 2259017 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.4116. Min Act: -0.1700
Data Index: 7509197 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.4116. Min Act: -0.1700
Data Index: 4050570 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.2866. Min Act: -0.1700
Data Index: 8154230 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.2553. Min Act: -0.1700
Data Index: 4201448 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.2241. Min Act: -0.1700
Data Index: 1912906 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.2241. Min Act: -0.1700
Data Index: 7094570 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.2241. Min Act: -0.1700
Data Index: 3304388 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.1928. Min Act: -0.1700
Data Index: 3759268 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.2241. Min Act: -0.1700
Data Index: 5757254 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.1928. Min Act: -0.1700
Data Index: 3125940 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.1928. Min Act: -0.1700
Data Index: 7101057 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.1616. Min Act: -0.1700
Data Index: 2177429 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.1616. Min Act: -0.1700
Data Index: 3958088 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.1616. Min Act: -0.1700
Data Index: 5398016 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.1303. Min Act: -0.1700
Data Index: 3874974 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.0991. Min Act: -0.1700
Data Index: 5703268 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.0991. Min Act: -0.1700
Data Index: 2716765 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.0991. Min Act: -0.1700
Data Index: 176818 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5678. Min Range: -5.5678
Max Act: 5.0678. Min Act: -0.1700
Data Index: 6781077 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19