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

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

Neuron 869 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: 1.6979. Min Range: -1.6979

Max Act: 1.6943. Min Act: -0.0001

Data Index: 575498 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.6979. Min Act: -0.0001

Data Index: 1230726 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.4208. Min Act: -0.0001

Data Index: 1124945 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.4477. Min Act: -0.0001

Data Index: 781765 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.3758. Min Act: -0.0001

Data Index: 571333 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.3610. Min Act: -0.0001

Data Index: 659 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.3334. Min Act: -0.0001

Data Index: 590556 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.3108. Min Act: -0.0001

Data Index: 99889 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2983. Min Act: -0.0001

Data Index: 139818 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2921. Min Act: -0.0001

Data Index: 914239 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2717. Min Act: -0.0001

Data Index: 1185100 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2594. Min Act: -0.0001

Data Index: 573525 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2460. Min Act: -0.0001

Data Index: 247528 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.3025. Min Act: -0.0001

Data Index: 428931 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2719. Min Act: -0.0001

Data Index: 1192133 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2178. Min Act: -0.0001

Data Index: 278159 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2839. Min Act: -0.0001

Data Index: 1022988 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.2010. Min Act: -0.0001

Data Index: 871211 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1882. Min Act: -0.0001

Data Index: 738203 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.6979. Min Range: -1.6979

Max Act: 1.1814. Min Act: -0.0001

Data Index: 655832 (C4 (Web Text))

Max Activating Token Index: 438