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

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

Neuron 4325 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: 5.0328. Min Range: -5.0328

Max Act: 5.0328. Min Act: -0.0000

Data Index: 649777 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 5.0328. Min Range: -5.0328

Max Act: 4.1864. Min Act: -0.0000

Data Index: 147344 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 5.0328. Min Range: -5.0328

Max Act: 4.0032. Min Act: -0.0000

Data Index: 933439 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.9468. Min Act: -0.0000

Data Index: 603148 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.9279. Min Act: -0.0000

Data Index: 624599 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.8925. Min Act: -0.0000

Data Index: 1238232 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.8403. Min Act: -0.0000

Data Index: 1132996 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.6818. Min Act: -0.0000

Data Index: 537972 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.8230. Min Act: -0.0000

Data Index: 940917 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.7787. Min Act: -0.0000

Data Index: 1286928 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.5470. Min Act: -0.0000

Data Index: 1224944 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.1630. Min Act: -0.0000

Data Index: 575647 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.4376. Min Act: -0.0000

Data Index: 828796 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.3628. Min Act: -0.0000

Data Index: 1222752 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.1997. Min Act: -0.0000

Data Index: 38018 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 5.0328. Min Range: -5.0328

Max Act: 2.8578. Min Act: -0.0000

Data Index: 242176 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.2966. Min Act: -0.0000

Data Index: 934696 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.2534. Min Act: -0.0000

Data Index: 140178 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.0720. Min Act: -0.0000

Data Index: 387826 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 5.0328. Min Range: -5.0328

Max Act: 3.0470. Min Act: -0.0000

Data Index: 908122 (C4 (Web Text))

Max Activating Token Index: 838