Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3144 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0496. Min Act: -0.0001

Data Index: 721378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0535. Min Act: -0.0001

Data Index: 312877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0001

Data Index: 534096 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1014300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0384. Min Act: -0.0001

Data Index: 384860 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0363. Min Act: -0.0002

Data Index: 325817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0329. Min Act: -0.0001

Data Index: 863211 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0390. Min Act: -0.0001

Data Index: 684568 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1240496 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1302687 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1241850 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0372. Min Act: -0.0001

Data Index: 169847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0367. Min Act: -0.0001

Data Index: 390406 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0248. Min Act: -0.0001

Data Index: 531427 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0319. Min Act: -0.0001

Data Index: 292478 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1123093 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1347102 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0274. Min Act: -0.0001

Data Index: 830060 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0299. Min Act: -0.0001

Data Index: 65659 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0399. Min Act: -0.0001

Data Index: 505936 (C4 (Web Text))

Max Activating Token Index: 1023