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

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

Neuron 3605 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.6080. Min Act: -0.0000

Data Index: 783474 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.5902. Min Act: -0.0000

Data Index: 989224 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.5951. Min Act: -0.0000

Data Index: 758296 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.5753. Min Act: -0.0000

Data Index: 307908 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.5193. Min Act: -0.0000

Data Index: 259590 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.4812. Min Act: -0.0000

Data Index: 300460 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.4294. Min Act: -0.0000

Data Index: 1334950 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.4288. Min Act: -0.0000

Data Index: 278167 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.4275. Min Act: -0.0000

Data Index: 1033245 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.3039. Min Act: -0.0000

Data Index: 875530 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.1870. Min Act: -0.0000

Data Index: 112074 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 3.6080. Min Range: -3.6080

Max Act: 2.9763. Min Act: -0.0000

Data Index: 1247115 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.1043. Min Act: -0.0000

Data Index: 631920 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 3.6080. Min Range: -3.6080

Max Act: 2.9482. Min Act: -0.0000

Data Index: 1265417 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.2200. Min Act: -0.0000

Data Index: 304801 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.6080. Min Range: -3.6080

Max Act: 2.9357. Min Act: -0.0000

Data Index: 541667 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.0376. Min Act: -0.0000

Data Index: 1303901 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.1723. Min Act: -0.0000

Data Index: 1298251 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 3.6080. Min Range: -3.6080

Max Act: 2.8503. Min Act: -0.0000

Data Index: 551229 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 3.6080. Min Range: -3.6080

Max Act: 3.0183. Min Act: -0.0000

Data Index: 1004493 (C4 (Web Text))

Max Activating Token Index: 949