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

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

Neuron 5349 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1295784 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1212. Min Act: -0.0001

Data Index: 937531 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0903. Min Act: -0.0001

Data Index: 782124 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0981. Min Act: -0.0001

Data Index: 23384 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0849. Min Act: -0.0001

Data Index: 74391 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0754. Min Act: -0.0001

Data Index: 662933 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1101274 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0855. Min Act: -0.0001

Data Index: 892710 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1170529 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0741. Min Act: -0.0001

Data Index: 513173 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0764. Min Act: -0.0001

Data Index: 98377 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1322474 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0729. Min Act: -0.0001

Data Index: 925251 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1249713 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0718. Min Act: -0.0001

Data Index: 507572 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0740. Min Act: -0.0001

Data Index: 365019 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0759. Min Act: -0.0001

Data Index: 313209 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0705. Min Act: -0.0001

Data Index: 124421 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0706. Min Act: -0.0001

Data Index: 623127 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0716. Min Act: -0.0001

Data Index: 399525 (C4 (Web Text))

Max Activating Token Index: 321