Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 952 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1417. Min Range: -8.1417
Max Act: 8.1417. Min Act: -0.1700
Data Index: 6028425 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1417. Min Range: -8.1417
Max Act: 8.0167. Min Act: -0.1700
Data Index: 6052189 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1417. Min Range: -8.1417
Max Act: 8.0167. Min Act: -0.1700
Data Index: 5105268 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1417. Min Range: -8.1417
Max Act: 8.0167. Min Act: -0.1700
Data Index: 415568 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.8917. Min Act: -0.1700
Data Index: 7216318 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.8292. Min Act: -0.1700
Data Index: 7698923 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.8292. Min Act: -0.1700
Data Index: 2843548 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.8917. Min Act: -0.1700
Data Index: 3649351 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7667. Min Act: -0.1700
Data Index: 1002797 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.8292. Min Act: -0.1700
Data Index: 3632810 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7667. Min Act: -0.1700
Data Index: 4862047 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7667. Min Act: -0.1700
Data Index: 99622 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7667. Min Act: -0.1700
Data Index: 2246217 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7042. Min Act: -0.1700
Data Index: 2796672 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7667. Min Act: -0.1700
Data Index: 826390 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7042. Min Act: -0.1700
Data Index: 8540004 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7042. Min Act: -0.1700
Data Index: 7711894 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.7042. Min Act: -0.1700
Data Index: 4185108 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.6417. Min Act: -0.1700
Data Index: 3729018 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1417. Min Range: -8.1417
Max Act: 7.6417. Min Act: -0.1700
Data Index: 6223850 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19