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

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

Neuron 1859 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2571. Min Act: -0.0001

Data Index: 392446 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2040. Min Act: -0.0001

Data Index: 296281 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2766. Min Act: -0.0001

Data Index: 877401 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2632. Min Act: -0.0001

Data Index: 708606 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1461. Min Act: -0.0001

Data Index: 116781 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1843. Min Act: -0.0001

Data Index: 726621 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1478. Min Act: -0.0001

Data Index: 117511 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1011. Min Act: -0.0001

Data Index: 358674 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1399. Min Act: -0.0001

Data Index: 121722 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0635. Min Act: -0.0001

Data Index: 269416 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1859. Min Act: -0.0001

Data Index: 780994 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0711. Min Act: -0.0001

Data Index: 732604 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1177. Min Act: -0.0001

Data Index: 914778 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1587. Min Act: -0.0001

Data Index: 91998 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0553. Min Act: -0.0001

Data Index: 439571 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1163. Min Act: -0.0001

Data Index: 44787 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0856. Min Act: -0.0001

Data Index: 679588 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1107. Min Act: -0.0001

Data Index: 974515 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0210. Min Act: -0.0001

Data Index: 198387 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9825. Min Act: -0.0001

Data Index: 41911 (C4 (Web Text))

Max Activating Token Index: 92