Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0001

Data Index: 297300 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1177585 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1530. Min Act: -0.0001

Data Index: 844129 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1578. Min Act: -0.0001

Data Index: 446448 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1146118 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1482. Min Act: -0.0001

Data Index: 959457 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1249731 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1321. Min Act: -0.0001

Data Index: 343574 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1255. Min Act: -0.0001

Data Index: 203156 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1323. Min Act: -0.0001

Data Index: 735164 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1559. Min Act: -0.0001

Data Index: 3291 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1266. Min Act: -0.0001

Data Index: 655308 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1295. Min Act: -0.0001

Data Index: 819789 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1291. Min Act: -0.0001

Data Index: 901691 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1361. Min Act: -0.0001

Data Index: 800717 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1272. Min Act: -0.0001

Data Index: 521235 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1356. Min Act: -0.0001

Data Index: 393142 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1200. Min Act: -0.0001

Data Index: 833941 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1216. Min Act: -0.0001

Data Index: 960401 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1251. Min Act: -0.0001

Data Index: 745265 (C4 (Web Text))

Max Activating Token Index: 420