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

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

Neuron 3651 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1553. Min Range: -4.1553

Max Act: 4.1553. Min Act: -0.0000

Data Index: 152003 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.9944. Min Act: -0.0000

Data Index: 473830 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.7147. Min Act: -0.0000

Data Index: 500316 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.8487. Min Act: -0.0000

Data Index: 1107919 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.6379. Min Act: -0.0000

Data Index: 18575 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.4187. Min Act: -0.0000

Data Index: 175091 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.2023. Min Act: -0.0000

Data Index: 120388 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.2851. Min Act: -0.0000

Data Index: 1007175 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.3986. Min Act: -0.0000

Data Index: 1334828 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.0678. Min Act: -0.0000

Data Index: 781899 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.0980. Min Act: -0.0000

Data Index: 389813 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.0030. Min Act: -0.0000

Data Index: 1318295 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.0638. Min Act: -0.0000

Data Index: 420203 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 4.1553. Min Range: -4.1553

Max Act: 2.9530. Min Act: -0.0000

Data Index: 283249 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.0890. Min Act: -0.0000

Data Index: 817418 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 4.1553. Min Range: -4.1553

Max Act: 3.0715. Min Act: -0.0000

Data Index: 4625 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 4.1553. Min Range: -4.1553

Max Act: 2.9305. Min Act: -0.0000

Data Index: 228926 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 4.1553. Min Range: -4.1553

Max Act: 2.8046. Min Act: -0.0000

Data Index: 909952 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 4.1553. Min Range: -4.1553

Max Act: 2.9299. Min Act: -0.0000

Data Index: 346243 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 4.1553. Min Range: -4.1553

Max Act: 2.7439. Min Act: -0.0000

Data Index: 944371 (C4 (Web Text))

Max Activating Token Index: 866