Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 312 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1357. Min Act: -0.0003

Data Index: 501409 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1427. Min Act: -0.0002

Data Index: 1157065 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1112319 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1234. Min Act: -0.0003

Data Index: 601218 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1226. Min Act: -0.0003

Data Index: 286976 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1195. Min Act: -0.0003

Data Index: 1316259 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1040. Min Act: -0.0003

Data Index: 973870 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0997. Min Act: -0.0003

Data Index: 348370 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1088. Min Act: -0.0003

Data Index: 779830 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1032. Min Act: -0.0003

Data Index: 197175 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1015. Min Act: -0.0002

Data Index: 654921 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1015. Min Act: -0.0002

Data Index: 119839 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1001. Min Act: -0.0003

Data Index: 621011 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0997. Min Act: -0.0003

Data Index: 531518 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0992. Min Act: -0.0003

Data Index: 801638 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1028. Min Act: -0.0003

Data Index: 285787 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0910. Min Act: -0.0002

Data Index: 238020 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0907. Min Act: -0.0002

Data Index: 392133 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0931. Min Act: -0.0002

Data Index: 939435 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.0936. Min Act: -0.0003

Data Index: 534217 (C4 (Web Text))

Max Activating Token Index: 642