Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5234 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1827. Min Range: -6.1827
Max Act: 6.1827. Min Act: -0.1700
Data Index: 7901191 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.9015. Min Act: -0.1700
Data Index: 1415275 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.8702. Min Act: -0.1700
Data Index: 1404067 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.8077. Min Act: -0.1700
Data Index: 5424461 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.7452. Min Act: -0.1700
Data Index: 6345992 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.7765. Min Act: -0.1700
Data Index: 3917184 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.7140. Min Act: -0.1700
Data Index: 7393328 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6827. Min Act: -0.1700
Data Index: 2137941 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6827. Min Act: -0.1700
Data Index: 8335211 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6827. Min Act: -0.1700
Data Index: 5778401 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6827. Min Act: -0.1700
Data Index: 5151413 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6515. Min Act: -0.1700
Data Index: 1503216 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6827. Min Act: -0.1700
Data Index: 5491251 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6515. Min Act: -0.1700
Data Index: 3580618 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6827. Min Act: -0.1700
Data Index: 5835167 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6202. Min Act: -0.1700
Data Index: 2083568 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6202. Min Act: -0.1700
Data Index: 6232084 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6202. Min Act: -0.1700
Data Index: 7259745 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6202. Min Act: -0.1700
Data Index: 5497402 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1827. Min Range: -6.1827
Max Act: 5.6202. Min Act: -0.1700
Data Index: 4101717 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19