Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4703 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2122. Min Range: -6.2122
Max Act: 6.2122. Min Act: -0.1700
Data Index: 8058933 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2122. Min Range: -6.2122
Max Act: 6.1185. Min Act: -0.1700
Data Index: 6316580 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2122. Min Range: -6.2122
Max Act: 6.1185. Min Act: -0.1700
Data Index: 1656180 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2122. Min Range: -6.2122
Max Act: 6.0247. Min Act: -0.1700
Data Index: 8477041 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2122. Min Range: -6.2122
Max Act: 6.0247. Min Act: -0.1700
Data Index: 5884978 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.9935. Min Act: -0.1700
Data Index: 154915 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.9622. Min Act: -0.1700
Data Index: 2863322 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.9310. Min Act: -0.1700
Data Index: 7261409 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8997. Min Act: -0.1700
Data Index: 4334769 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8372. Min Act: -0.1700
Data Index: 7267522 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8685. Min Act: -0.1700
Data Index: 4413338 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8372. Min Act: -0.1700
Data Index: 7783241 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8060. Min Act: -0.1700
Data Index: 632132 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8060. Min Act: -0.1700
Data Index: 3387146 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8060. Min Act: -0.1700
Data Index: 4257569 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8060. Min Act: -0.1700
Data Index: 3827366 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.8060. Min Act: -0.1700
Data Index: 5471557 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.7747. Min Act: -0.1700
Data Index: 2814241 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.7747. Min Act: -0.1700
Data Index: 5775127 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2122. Min Range: -6.2122
Max Act: 5.7435. Min Act: -0.1700
Data Index: 6376176 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19