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

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

Neuron 3786 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.5513. Min Act: -0.0000

Data Index: 929642 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.3215. Min Act: -0.0000

Data Index: 964288 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.2619. Min Act: -0.0000

Data Index: 277296 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.2328. Min Act: -0.0000

Data Index: 156039 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.1458. Min Act: -0.0000

Data Index: 322353 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1001145 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.1321. Min Act: -0.0000

Data Index: 724160 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1175717 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1003514 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0982. Min Act: -0.0000

Data Index: 828526 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0247. Min Act: -0.0000

Data Index: 858122 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0883. Min Act: -0.0000

Data Index: 819879 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1353110 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0169. Min Act: -0.0000

Data Index: 757157 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0455. Min Act: -0.0000

Data Index: 971017 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1202290 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0693. Min Act: -0.0000

Data Index: 327955 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1168920 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 1.5513. Min Range: -1.5513

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1095513 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 1.5513. Min Range: -1.5513

Max Act: 0.9916. Min Act: -0.0000

Data Index: 231345 (C4 (Web Text))

Max Activating Token Index: 333