Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2655 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.6589. Min Act: -0.0000

Data Index: 654294 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.4876. Min Act: -0.0000

Data Index: 1029937 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1155953 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.2258. Min Act: -0.0000

Data Index: 889117 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1111. Min Act: -0.0000

Data Index: 865118 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0526. Min Act: -0.0000

Data Index: 460900 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0933. Min Act: -0.0000

Data Index: 681362 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0578. Min Act: -0.0000

Data Index: 32498 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0559. Min Act: -0.0000

Data Index: 404059 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1118963 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0223. Min Act: -0.0000

Data Index: 643675 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0179. Min Act: 0.0000

Data Index: 617505 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.6589. Min Range: -1.6589

Max Act: 0.9529. Min Act: -0.0000

Data Index: 686342 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 1.6589. Min Range: -1.6589

Max Act: 1.0078. Min Act: -0.0000

Data Index: 889529 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.6589. Min Range: -1.6589

Max Act: 0.9253. Min Act: -0.0000

Data Index: 390796 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.6589. Min Range: -1.6589

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1301690 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.6589. Min Range: -1.6589

Max Act: 0.9013. Min Act: -0.0000

Data Index: 319329 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.6589. Min Range: -1.6589

Max Act: 0.9528. Min Act: -0.0000

Data Index: 796249 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 1.6589. Min Range: -1.6589

Max Act: 0.9509. Min Act: -0.0000

Data Index: 853256 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.6589. Min Range: -1.6589

Max Act: 0.9889. Min Act: -0.0000

Data Index: 582220 (C4 (Web Text))

Max Activating Token Index: 981