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

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

Neuron 4474 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2444. Min Act: -0.0000

Data Index: 217648 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2262. Min Act: -0.0000

Data Index: 387319 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2070. Min Act: -0.0000

Data Index: 426516 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2300. Min Act: -0.0000

Data Index: 1243245 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2263. Min Act: -0.0000

Data Index: 953038 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1170498 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1262378 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1184565 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2020. Min Act: -0.0000

Data Index: 963511 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1943. Min Act: -0.0000

Data Index: 97172 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1843. Min Act: -0.0000

Data Index: 454119 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1824. Min Act: -0.0000

Data Index: 25305 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1852. Min Act: -0.0000

Data Index: 949093 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1788. Min Act: -0.0000

Data Index: 230577 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1898. Min Act: -0.0000

Data Index: 744520 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1690. Min Act: -0.0000

Data Index: 399224 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1918. Min Act: -0.0000

Data Index: 52763 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1681. Min Act: -0.0000

Data Index: 694708 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1026433 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1734. Min Act: -0.0000

Data Index: 393646 (C4 (Web Text))

Max Activating Token Index: 682