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

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

Neuron 2790 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0386. Min Range: -1.0386

Max Act: 1.0386. Min Act: -0.0001

Data Index: 443668 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8407. Min Act: -0.0001

Data Index: 958763 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8961. Min Act: -0.0001

Data Index: 210119 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8244. Min Act: -0.0001

Data Index: 1358622 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7433. Min Act: -0.0001

Data Index: 364205 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1040883 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1080999 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.8422. Min Act: -0.0000

Data Index: 713585 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7761. Min Act: -0.0001

Data Index: 799146 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1056033 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7616. Min Act: -0.0001

Data Index: 1258702 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7483. Min Act: -0.0001

Data Index: 543817 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6926. Min Act: -0.0000

Data Index: 944204 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1254600 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6195. Min Act: -0.0001

Data Index: 471875 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6973. Min Act: -0.0001

Data Index: 640371 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.7005. Min Act: -0.0001

Data Index: 81691 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6472. Min Act: -0.0001

Data Index: 948624 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6943. Min Act: -0.0001

Data Index: 793745 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.0386. Min Range: -1.0386

Max Act: 0.6660. Min Act: -0.0001

Data Index: 1162169 (C4 (Web Text))

Max Activating Token Index: 435