Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5660 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.6666. Min Act: -0.1700
Data Index: 7178682 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.5416. Min Act: -0.1700
Data Index: 3103415 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.5103. Min Act: -0.1700
Data Index: 4587302 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.4478. Min Act: -0.1700
Data Index: 4910280 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.4166. Min Act: -0.1700
Data Index: 223635 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.4166. Min Act: -0.1700
Data Index: 4419178 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.4166. Min Act: -0.1700
Data Index: 2742728 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.4166. Min Act: -0.1700
Data Index: 4832112 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.3853. Min Act: -0.1700
Data Index: 1958730 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.3853. Min Act: -0.1700
Data Index: 7238879 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.3541. Min Act: -0.1700
Data Index: 868299 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.3541. Min Act: -0.1700
Data Index: 2290978 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.2916. Min Act: -0.1700
Data Index: 2204980 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.2603. Min Act: -0.1700
Data Index: 4985947 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.2603. Min Act: -0.1700
Data Index: 2757466 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.2291. Min Act: -0.1700
Data Index: 6417593 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.2603. Min Act: -0.1700
Data Index: 4822992 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.2291. Min Act: -0.1700
Data Index: 2806873 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.1978. Min Act: -0.1700
Data Index: 7077161 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6666. Min Range: -6.6666
Max Act: 6.1978. Min Act: -0.1700
Data Index: 3594361 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19