Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2291 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.9288. Min Act: -0.1700
Data Index: 8565067 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.8350. Min Act: -0.1700
Data Index: 4683642 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.7100. Min Act: -0.1700
Data Index: 5361385 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.7100. Min Act: -0.1700
Data Index: 649903 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.6163. Min Act: -0.1700
Data Index: 7446244 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.6163. Min Act: -0.1700
Data Index: 5105774 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.6163. Min Act: -0.1700
Data Index: 1509064 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.5850. Min Act: -0.1700
Data Index: 7310866 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.5850. Min Act: -0.1700
Data Index: 2278791 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.5538. Min Act: -0.1700
Data Index: 24409 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.5850. Min Act: -0.1700
Data Index: 7460440 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.5225. Min Act: -0.1700
Data Index: 2201962 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.5225. Min Act: -0.1700
Data Index: 6353769 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.5225. Min Act: -0.1700
Data Index: 5607310 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.4913. Min Act: -0.1700
Data Index: 8270790 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.4913. Min Act: -0.1700
Data Index: 3904634 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.4600. Min Act: -0.1700
Data Index: 8814854 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.4600. Min Act: -0.1700
Data Index: 8262662 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.4288. Min Act: -0.1700
Data Index: 2060439 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9288. Min Range: -5.9288
Max Act: 5.4288. Min Act: -0.1700
Data Index: 230058 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19