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

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

Neuron 63 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5317. Min Range: -3.5317

Max Act: 3.5317. Min Act: -0.0000

Data Index: 889848 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 3.5317. Min Range: -3.5317

Max Act: 3.2564. Min Act: -0.0000

Data Index: 541656 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.4656. Min Act: -0.0000

Data Index: 176878 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.7132. Min Act: -0.0000

Data Index: 425764 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.3593. Min Act: -0.0000

Data Index: 1322724 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.3511. Min Act: -0.0000

Data Index: 334788 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.2038. Min Act: -0.0000

Data Index: 971326 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.7263. Min Act: -0.0000

Data Index: 1190691 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.5805. Min Act: -0.0000

Data Index: 253294 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.3574. Min Act: -0.0000

Data Index: 829548 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.3560. Min Act: -0.0000

Data Index: 577843 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.3178. Min Act: -0.0000

Data Index: 202353 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.2669. Min Act: -0.0000

Data Index: 180523 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.5653. Min Act: -0.0000

Data Index: 849530 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.2961. Min Act: -0.0000

Data Index: 443083 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.1656. Min Act: -0.0000

Data Index: 950810 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.1370. Min Act: -0.0000

Data Index: 1352050 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.0169. Min Act: -0.0000

Data Index: 564943 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.0115. Min Act: -0.0000

Data Index: 1025800 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 3.5317. Min Range: -3.5317

Max Act: 2.1831. Min Act: -0.0000

Data Index: 119629 (C4 (Web Text))

Max Activating Token Index: 504