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

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

Neuron 4557 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: 6.1532. Min Range: -6.1532

Max Act: 6.1532. Min Act: -0.0000

Data Index: 2240 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 6.1532. Min Range: -6.1532

Max Act: 6.1418. Min Act: -0.0000

Data Index: 102392 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 6.1532. Min Range: -6.1532

Max Act: 5.7989. Min Act: -0.0000

Data Index: 911922 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 6.1532. Min Range: -6.1532

Max Act: 5.9874. Min Act: -0.0000

Data Index: 738690 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 6.1532. Min Range: -6.1532

Max Act: 5.1771. Min Act: -0.0000

Data Index: 1047683 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 6.1532. Min Range: -6.1532

Max Act: 5.3681. Min Act: -0.0000

Data Index: 234526 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.8854. Min Act: -0.0000

Data Index: 8936 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 6.1532. Min Range: -6.1532

Max Act: 5.0789. Min Act: -0.0000

Data Index: 318798 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.4401. Min Act: -0.0000

Data Index: 432206 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.9622. Min Act: -0.0000

Data Index: 1121480 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.9291. Min Act: -0.0000

Data Index: 35242 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.9054. Min Act: -0.0000

Data Index: 1030567 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.4463. Min Act: -0.0000

Data Index: 338404 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.9246. Min Act: -0.0000

Data Index: 298058 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.5214. Min Act: -0.0000

Data Index: 305329 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.4644. Min Act: -0.0000

Data Index: 254285 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.2181. Min Act: -0.0000

Data Index: 311020 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.4274. Min Act: -0.0000

Data Index: 1127005 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.3595. Min Act: -0.0000

Data Index: 176633 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 6.1532. Min Range: -6.1532

Max Act: 4.1179. Min Act: -0.0000

Data Index: 1222855 (C4 (Web Text))

Max Activating Token Index: 970