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

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

Neuron 3570 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.8290. Min Act: -0.0001

Data Index: 1293262 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.8039. Min Act: -0.0001

Data Index: 13030 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.8436. Min Act: -0.0001

Data Index: 707145 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.9206. Min Act: -0.0001

Data Index: 278915 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7744. Min Act: -0.0001

Data Index: 979740 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7553. Min Act: -0.0001

Data Index: 1230186 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.8447. Min Act: -0.0001

Data Index: 731882 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7629. Min Act: -0.0001

Data Index: 729001 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7577. Min Act: -0.0001

Data Index: 896283 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7455. Min Act: -0.0001

Data Index: 1090512 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7845. Min Act: -0.0001

Data Index: 682297 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.8802. Min Act: -0.0001

Data Index: 435102 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7723. Min Act: -0.0001

Data Index: 724024 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7680. Min Act: -0.0001

Data Index: 430575 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.6627. Min Act: -0.0001

Data Index: 572784 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.8004. Min Act: -0.0001

Data Index: 977790 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7867. Min Act: -0.0001

Data Index: 876576 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.6522. Min Act: -0.0001

Data Index: 1191977 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7885. Min Act: -0.0001

Data Index: 387898 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.9206. Min Range: -1.9206

Max Act: 1.7325. Min Act: -0.0001

Data Index: 95798 (C4 (Web Text))

Max Activating Token Index: 765