Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5771 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4086. Min Range: -8.4086
Max Act: 8.4086. Min Act: -0.1700
Data Index: 1451882 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4086. Min Range: -8.4086
Max Act: 8.2211. Min Act: -0.1700
Data Index: 4225490 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4086. Min Range: -8.4086
Max Act: 8.2836. Min Act: -0.1700
Data Index: 1034892 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4086. Min Range: -8.4086
Max Act: 8.2211. Min Act: -0.1700
Data Index: 4173140 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4086. Min Range: -8.4086
Max Act: 8.0961. Min Act: -0.1700
Data Index: 5011280 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4086. Min Range: -8.4086
Max Act: 8.0336. Min Act: -0.1700
Data Index: 8025145 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.9711. Min Act: -0.1700
Data Index: 8088540 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.7211. Min Act: -0.1700
Data Index: 157240 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.8461. Min Act: -0.1700
Data Index: 3965661 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.7836. Min Act: -0.1700
Data Index: 8133415 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.7211. Min Act: -0.1700
Data Index: 1103160 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.7211. Min Act: -0.1700
Data Index: 5784920 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.7211. Min Act: -0.1700
Data Index: 4940218 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.7211. Min Act: -0.1700
Data Index: 5887306 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.7211. Min Act: -0.1700
Data Index: 5631672 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.6586. Min Act: -0.1700
Data Index: 1642153 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.6586. Min Act: -0.1700
Data Index: 4700142 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.6274. Min Act: -0.1700
Data Index: 6795232 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.6274. Min Act: -0.1700
Data Index: 3082544 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4086. Min Range: -8.4086
Max Act: 7.6274. Min Act: -0.1700
Data Index: 1354934 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19