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

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

Neuron 2765 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.2069. Min Act: -0.0002

Data Index: 136839 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1943. Min Act: -0.0002

Data Index: 189199 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1793. Min Act: -0.0002

Data Index: 147230 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1899. Min Act: -0.0002

Data Index: 397967 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1879. Min Act: -0.0002

Data Index: 656887 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1681. Min Act: -0.0001

Data Index: 951859 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1705. Min Act: -0.0002

Data Index: 265757 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1604. Min Act: -0.0001

Data Index: 130 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1697. Min Act: -0.0001

Data Index: 522312 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1676. Min Act: -0.0001

Data Index: 849056 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1569. Min Act: -0.0001

Data Index: 823590 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1725. Min Act: -0.0002

Data Index: 1197503 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1604. Min Act: -0.0001

Data Index: 166245 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1724. Min Act: -0.0001

Data Index: 622760 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1622. Min Act: -0.0001

Data Index: 267364 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1568. Min Act: -0.0002

Data Index: 217364 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1612. Min Act: -0.0002

Data Index: 251574 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1643. Min Act: -0.0002

Data Index: 1160312 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1501. Min Act: -0.0001

Data Index: 295091 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1669. Min Act: -0.0001

Data Index: 299653 (C4 (Web Text))

Max Activating Token Index: 1008