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

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

Neuron 4990 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.5117. Min Act: -0.0000

Data Index: 1129015 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.6431. Min Act: -0.0000

Data Index: 372034 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.5041. Min Act: -0.0000

Data Index: 994260 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.4571. Min Act: -0.0000

Data Index: 736721 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1208729 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2916. Min Act: -0.0000

Data Index: 11058 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.3010. Min Act: -0.0000

Data Index: 174181 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2053. Min Act: -0.0000

Data Index: 899295 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1013737 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1990. Min Act: -0.0000

Data Index: 551871 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1857. Min Act: -0.0000

Data Index: 630997 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1897. Min Act: 0.0000

Data Index: 46703 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1562. Min Act: -0.0000

Data Index: 135224 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1521. Min Act: -0.0000

Data Index: 328716 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1503. Min Act: -0.0000

Data Index: 73063 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1046. Min Act: -0.0000

Data Index: 810636 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1205. Min Act: -0.0000

Data Index: 1193620 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1274. Min Act: 0.0000

Data Index: 1331080 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1075. Min Act: -0.0000

Data Index: 615066 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.0156. Min Act: -0.0000

Data Index: 28109 (C4 (Web Text))

Max Activating Token Index: 355