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

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

Neuron 876 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: 0.1122. Min Range: -0.1122

Max Act: 0.1122. Min Act: -0.0003

Data Index: 781278 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1007. Min Act: -0.0003

Data Index: 808311 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0984. Min Act: -0.0003

Data Index: 286976 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0978. Min Act: -0.0003

Data Index: 37405 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0984. Min Act: -0.0003

Data Index: 46686 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0976. Min Act: -0.0003

Data Index: 351171 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0958. Min Act: -0.0004

Data Index: 184900 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0935. Min Act: -0.0004

Data Index: 1027012 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0946. Min Act: -0.0003

Data Index: 899685 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0936. Min Act: -0.0004

Data Index: 788572 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0963. Min Act: -0.0003

Data Index: 801284 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0934. Min Act: -0.0003

Data Index: 171662 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0917. Min Act: -0.0003

Data Index: 418100 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0923. Min Act: -0.0002

Data Index: 917137 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0909. Min Act: -0.0003

Data Index: 886031 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0916. Min Act: -0.0002

Data Index: 603372 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0911. Min Act: -0.0003

Data Index: 1156739 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0912. Min Act: -0.0004

Data Index: 1262624 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1356705 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0864. Min Act: -0.0003

Data Index: 549580 (C4 (Web Text))

Max Activating Token Index: 44