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

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

Neuron 933 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.6511. Min Act: -0.0000

Data Index: 273713 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.6420. Min Act: -0.0000

Data Index: 42709 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.3541. Min Act: -0.0000

Data Index: 345361 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.1691. Min Act: -0.0000

Data Index: 256248 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.2898. Min Act: -0.0000

Data Index: 785835 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.1012. Min Act: -0.0000

Data Index: 1180084 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.2205. Min Act: -0.0000

Data Index: 317705 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.1595. Min Act: -0.0000

Data Index: 101867 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 2.6511. Min Range: -2.6511

Max Act: 2.0404. Min Act: -0.0000

Data Index: 113518 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1318611 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1127007 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.9396. Min Act: -0.0000

Data Index: 17705 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.9093. Min Act: -0.0000

Data Index: 384357 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.7977. Min Act: -0.0000

Data Index: 541477 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.7933. Min Act: -0.0000

Data Index: 456121 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.7749. Min Act: -0.0000

Data Index: 370331 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.8585. Min Act: -0.0000

Data Index: 922564 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.6513. Min Act: -0.0000

Data Index: 1152706 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.7495. Min Act: -0.0000

Data Index: 193299 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 2.6511. Min Range: -2.6511

Max Act: 1.8236. Min Act: -0.0000

Data Index: 596871 (C4 (Web Text))

Max Activating Token Index: 103