Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3551 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1476. Min Range: -3.1476

Max Act: 3.1476. Min Act: -0.0000

Data Index: 697558 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.6242. Min Act: -0.0000

Data Index: 223732 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.1753. Min Act: -0.0000

Data Index: 117935 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.3105. Min Act: -0.0000

Data Index: 389500 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.2479. Min Act: -0.0000

Data Index: 1255663 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.1216. Min Act: -0.0000

Data Index: 277743 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.0798. Min Act: -0.0000

Data Index: 1194278 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.0628. Min Act: -0.0000

Data Index: 591593 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.0175. Min Act: -0.0000

Data Index: 1153975 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.1270. Min Act: -0.0000

Data Index: 1298268 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.0772. Min Act: -0.0000

Data Index: 1287806 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.0474. Min Act: -0.0000

Data Index: 346595 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.1476. Min Range: -3.1476

Max Act: 1.8153. Min Act: -0.0000

Data Index: 1092745 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 3.1476. Min Range: -3.1476

Max Act: 1.9427. Min Act: -0.0000

Data Index: 198263 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.1476. Min Range: -3.1476

Max Act: 2.0199. Min Act: -0.0000

Data Index: 305530 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 3.1476. Min Range: -3.1476

Max Act: 1.9922. Min Act: -0.0000

Data Index: 216377 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 3.1476. Min Range: -3.1476

Max Act: 1.8643. Min Act: -0.0000

Data Index: 570605 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 3.1476. Min Range: -3.1476

Max Act: 1.8835. Min Act: -0.0000

Data Index: 386700 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 3.1476. Min Range: -3.1476

Max Act: 1.9746. Min Act: -0.0000

Data Index: 721420 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 3.1476. Min Range: -3.1476

Max Act: 1.9707. Min Act: -0.0000

Data Index: 715473 (C4 (Web Text))

Max Activating Token Index: 321