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

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

Neuron 557 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: 1.0458. Min Range: -1.0458

Max Act: 0.9597. Min Act: -0.0001

Data Index: 970305 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.0458. Min Range: -1.0458

Max Act: 1.0131. Min Act: -0.0001

Data Index: 116080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9634. Min Act: -0.0001

Data Index: 1176151 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9891. Min Act: -0.0001

Data Index: 19621 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.0458. Min Range: -1.0458

Max Act: 1.0218. Min Act: -0.0001

Data Index: 244984 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9579. Min Act: -0.0001

Data Index: 744843 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 1.0458. Min Range: -1.0458

Max Act: 1.0234. Min Act: -0.0001

Data Index: 200158 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.0458. Min Range: -1.0458

Max Act: 1.0458. Min Act: -0.0001

Data Index: 1283447 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9578. Min Act: -0.0001

Data Index: 992853 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8998. Min Act: -0.0001

Data Index: 94093 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8587. Min Act: -0.0001

Data Index: 970332 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8668. Min Act: -0.0001

Data Index: 535118 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8840. Min Act: -0.0001

Data Index: 94839 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8892. Min Act: -0.0001

Data Index: 781443 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8432. Min Act: -0.0001

Data Index: 863179 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8232. Min Act: -0.0001

Data Index: 894569 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8520. Min Act: -0.0001

Data Index: 1253165 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8459. Min Act: -0.0001

Data Index: 1164450 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8448. Min Act: -0.0001

Data Index: 1241404 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7912. Min Act: -0.0001

Data Index: 599094 (C4 (Web Text))

Max Activating Token Index: 812