Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.2229. Min Act: -0.0000

Data Index: 647153 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.2446. Min Act: -0.0000

Data Index: 1132979 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.2100. Min Act: -0.0000

Data Index: 282084 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.1082. Min Act: -0.0000

Data Index: 211732 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1212805 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0824. Min Act: -0.0000

Data Index: 351547 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0540. Min Act: -0.0000

Data Index: 277917 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0823. Min Act: -0.0000

Data Index: 335875 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9994. Min Act: -0.0000

Data Index: 291905 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0801. Min Act: -0.0000

Data Index: 87986 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0741. Min Act: -0.0000

Data Index: 571894 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0408. Min Act: -0.0000

Data Index: 1116302 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0639. Min Act: -0.0000

Data Index: 1006186 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0403. Min Act: -0.0000

Data Index: 403641 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1087337 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0148. Min Act: -0.0000

Data Index: 295971 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9693. Min Act: -0.0000

Data Index: 86187 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9870. Min Act: -0.0000

Data Index: 738188 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1196664 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8772. Min Act: -0.0000

Data Index: 80344 (C4 (Web Text))

Max Activating Token Index: 802