Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0856. Min Act: -0.0002

Data Index: 824635 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1113907 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1045115 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0817. Min Act: -0.0002

Data Index: 362307 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1104378 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0785. Min Act: -0.0002

Data Index: 762398 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1516930 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1094793 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1116584 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0799. Min Act: -0.0001

Data Index: 299440 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0758. Min Act: -0.0002

Data Index: 335990 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1212022 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0754. Min Act: -0.0002

Data Index: 487451 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1141814 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1444646 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0750. Min Act: -0.0002

Data Index: 41925 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0745. Min Act: -0.0002

Data Index: 795654 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0768. Min Act: -0.0002

Data Index: 621950 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1375149 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1152007 (C4 (Web Text))

Max Activating Token Index: 886