Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5608 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1173909 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1341. Min Act: -0.0001

Data Index: 810886 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1049. Min Act: -0.0001

Data Index: 320724 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1175957 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1090. Min Act: -0.0001

Data Index: 926678 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1004. Min Act: -0.0001

Data Index: 35623 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1106. Min Act: -0.0001

Data Index: 459026 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1265637 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0947. Min Act: -0.0001

Data Index: 872586 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0936. Min Act: -0.0001

Data Index: 418605 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0952. Min Act: -0.0001

Data Index: 823872 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0881. Min Act: -0.0001

Data Index: 994763 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0936. Min Act: -0.0001

Data Index: 573078 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0996. Min Act: -0.0001

Data Index: 18023 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0981. Min Act: -0.0001

Data Index: 995637 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0787. Min Act: -0.0001

Data Index: 673300 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0935. Min Act: -0.0001

Data Index: 90765 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0977. Min Act: -0.0001

Data Index: 828491 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0905. Min Act: -0.0001

Data Index: 282944 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0900. Min Act: -0.0001

Data Index: 98351 (C4 (Web Text))

Max Activating Token Index: 819