Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4049 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9143. Min Range: -2.9143

Max Act: 2.9143. Min Act: -0.0000

Data Index: 916567 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 2.9143. Min Range: -2.9143

Max Act: 2.6389. Min Act: -0.0000

Data Index: 769055 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 2.9143. Min Range: -2.9143

Max Act: 2.2181. Min Act: -0.0000

Data Index: 1291870 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 2.9143. Min Range: -2.9143

Max Act: 2.1079. Min Act: -0.0000

Data Index: 832474 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 2.9143. Min Range: -2.9143

Max Act: 2.1440. Min Act: -0.0000

Data Index: 959740 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.9166. Min Act: -0.0000

Data Index: 809437 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 2.9143. Min Range: -2.9143

Max Act: 2.1271. Min Act: -0.0000

Data Index: 1035383 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.8435. Min Act: -0.0000

Data Index: 1328044 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.6831. Min Act: -0.0000

Data Index: 594578 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.7000. Min Act: -0.0000

Data Index: 156272 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1019172 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.8015. Min Act: -0.0000

Data Index: 992014 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.9210. Min Act: -0.0000

Data Index: 709448 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.9817. Min Act: -0.0000

Data Index: 317828 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.8554. Min Act: -0.0000

Data Index: 490027 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.5839. Min Act: -0.0000

Data Index: 41696 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.6239. Min Act: -0.0000

Data Index: 206467 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.4540. Min Act: -0.0000

Data Index: 870792 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.5243. Min Act: -0.0000

Data Index: 1195524 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 2.9143. Min Range: -2.9143

Max Act: 1.4430. Min Act: -0.0000

Data Index: 95585 (C4 (Web Text))

Max Activating Token Index: 1020