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

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

Neuron 2718 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5238. Min Range: -4.5238

Max Act: 4.5238. Min Act: -0.0000

Data Index: 364321 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.9012. Min Act: -0.0000

Data Index: 885884 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.7744. Min Act: -0.0000

Data Index: 952886 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.7099. Min Act: -0.0000

Data Index: 1321751 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.6772. Min Act: -0.0000

Data Index: 944102 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.4191. Min Act: -0.0000

Data Index: 882157 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.5729. Min Act: -0.0000

Data Index: 872143 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.5341. Min Act: -0.0000

Data Index: 678493 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.5235. Min Act: -0.0000

Data Index: 143253 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.5368. Min Act: -0.0000

Data Index: 940608 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.1187. Min Act: -0.0000

Data Index: 1148544 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.4510. Min Act: -0.0000

Data Index: 373875 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.4367. Min Act: -0.0000

Data Index: 1211169 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.3023. Min Act: -0.0000

Data Index: 85685 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.2413. Min Act: -0.0000

Data Index: 157654 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.3482. Min Act: -0.0000

Data Index: 1201572 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.1474. Min Act: -0.0000

Data Index: 1217391 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.1806. Min Act: -0.0000

Data Index: 1272135 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.1810. Min Act: -0.0000

Data Index: 872347 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 4.5238. Min Range: -4.5238

Max Act: 2.1808. Min Act: -0.0000

Data Index: 58783 (C4 (Web Text))

Max Activating Token Index: 570