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

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

Neuron 101 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1554. Min Act: -0.0001

Data Index: 293869 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1431. Min Act: -0.0001

Data Index: 914821 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1362. Min Act: -0.0001

Data Index: 599649 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1312. Min Act: -0.0001

Data Index: 852072 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1349. Min Act: -0.0001

Data Index: 104534 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1322. Min Act: -0.0001

Data Index: 868260 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1302. Min Act: -0.0001

Data Index: 383733 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1251. Min Act: -0.0001

Data Index: 273639 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1258. Min Act: -0.0001

Data Index: 310064 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1259. Min Act: -0.0001

Data Index: 803306 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1178620 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1304. Min Act: -0.0001

Data Index: 315190 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1225. Min Act: -0.0001

Data Index: 549322 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1268649 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1224. Min Act: -0.0001

Data Index: 828432 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1220. Min Act: -0.0001

Data Index: 342453 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1127. Min Act: -0.0001

Data Index: 670845 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1207. Min Act: -0.0001

Data Index: 565231 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1182. Min Act: -0.0001

Data Index: 297734 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1077273 (C4 (Web Text))

Max Activating Token Index: 565