Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3583 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.6427. Min Act: -0.0000

Data Index: 822283 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.4473. Min Act: -0.0000

Data Index: 517857 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.5025. Min Act: -0.0000

Data Index: 51498 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1239498 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1146267 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3732. Min Act: -0.0000

Data Index: 591926 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3322. Min Act: -0.0000

Data Index: 374027 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3362. Min Act: -0.0000

Data Index: 682563 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3079. Min Act: -0.0000

Data Index: 121206 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.2304. Min Act: -0.0000

Data Index: 733471 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.0461. Min Act: -0.0000

Data Index: 675546 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3501. Min Act: -0.0000

Data Index: 620769 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1761. Min Act: -0.0000

Data Index: 90154 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.2370. Min Act: -0.0000

Data Index: 351204 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1917. Min Act: -0.0000

Data Index: 641861 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1623. Min Act: -0.0000

Data Index: 375141 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1291202 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1200752 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.2991. Min Act: -0.0000

Data Index: 1216202 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.0402. Min Act: -0.0000

Data Index: 693031 (C4 (Web Text))

Max Activating Token Index: 977