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

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

Neuron 3280 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.3194. Min Act: -0.0001

Data Index: 823084 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2774. Min Act: -0.0001

Data Index: 144202 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2652. Min Act: -0.0001

Data Index: 1085374 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2610. Min Act: -0.0001

Data Index: 907148 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2576. Min Act: -0.0001

Data Index: 278153 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2503. Min Act: -0.0001

Data Index: 392748 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2428. Min Act: -0.0001

Data Index: 991445 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1002 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2491. Min Act: -0.0001

Data Index: 231023 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2448. Min Act: -0.0001

Data Index: 781279 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1359093 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2395. Min Act: -0.0001

Data Index: 268712 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2245. Min Act: -0.0001

Data Index: 301142 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1072114 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2433. Min Act: -0.0001

Data Index: 555473 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2213. Min Act: -0.0001

Data Index: 1293215 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2201. Min Act: -0.0001

Data Index: 76708 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1096466 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2100. Min Act: -0.0001

Data Index: 937708 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2162. Min Act: -0.0001

Data Index: 355295 (C4 (Web Text))

Max Activating Token Index: 964