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

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

Neuron 3013 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.2541. Min Act: -0.0000

Data Index: 122603 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.2446. Min Act: -0.0000

Data Index: 1069407 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.1890. Min Act: -0.0000

Data Index: 677074 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0749. Min Act: -0.0000

Data Index: 889177 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.1387. Min Act: -0.0000

Data Index: 962521 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.1102. Min Act: -0.0000

Data Index: 922678 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0764. Min Act: -0.0000

Data Index: 511313 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0475. Min Act: -0.0000

Data Index: 29690 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0243. Min Act: -0.0000

Data Index: 802976 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1126546 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9104. Min Act: -0.0000

Data Index: 69224 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1316951 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1223764 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8662. Min Act: -0.0000

Data Index: 254577 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1254984 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8282. Min Act: -0.0000

Data Index: 923928 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8167. Min Act: -0.0000

Data Index: 30707 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8117. Min Act: -0.0000

Data Index: 667650 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8012. Min Act: -0.0000

Data Index: 320339 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.7384. Min Act: -0.0000

Data Index: 400595 (C4 (Web Text))

Max Activating Token Index: 468