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

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

Neuron 671 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: 0.1337. Min Range: -0.1337

Max Act: 0.1337. Min Act: -0.0003

Data Index: 1053628 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1064. Min Act: -0.0003

Data Index: 784915 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1075. Min Act: -0.0003

Data Index: 1049274 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1016. Min Act: -0.0003

Data Index: 75790 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0972. Min Act: -0.0003

Data Index: 492805 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0920. Min Act: -0.0003

Data Index: 1316876 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0930. Min Act: -0.0003

Data Index: 566439 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0949. Min Act: -0.0003

Data Index: 1277487 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0862. Min Act: -0.0004

Data Index: 676064 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0898. Min Act: -0.0004

Data Index: 262111 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0925. Min Act: -0.0003

Data Index: 504409 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0884. Min Act: -0.0003

Data Index: 188017 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0881. Min Act: -0.0003

Data Index: 518721 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0892. Min Act: -0.0003

Data Index: 752697 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0858. Min Act: -0.0003

Data Index: 685789 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1044309 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0863. Min Act: -0.0003

Data Index: 646717 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0830. Min Act: -0.0002

Data Index: 721851 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0856. Min Act: -0.0003

Data Index: 608469 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1227981 (C4 (Web Text))

Max Activating Token Index: 886