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

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

Neuron 28 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.3245. Min Act: -0.0003

Data Index: 776542 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2265. Min Act: -0.0003

Data Index: 44120 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0375. Min Act: -0.0003

Data Index: 1302577 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0796. Min Act: -0.0003

Data Index: 1054003 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0737. Min Act: -0.0003

Data Index: 409954 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0257. Min Act: -0.0003

Data Index: 87789 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0554. Min Act: -0.0003

Data Index: 1219531 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0788. Min Act: -0.0003

Data Index: 1135093 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9574. Min Act: -0.0003

Data Index: 446893 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0392. Min Act: -0.0003

Data Index: 860759 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9749. Min Act: -0.0003

Data Index: 760371 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0584. Min Act: -0.0003

Data Index: 165482 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9948. Min Act: -0.0003

Data Index: 615743 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9946. Min Act: -0.0003

Data Index: 581419 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0323. Min Act: -0.0003

Data Index: 873834 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9686. Min Act: -0.0003

Data Index: 366344 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9698. Min Act: -0.0003

Data Index: 448433 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0004. Min Act: -0.0003

Data Index: 999304 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9348. Min Act: -0.0003

Data Index: 445895 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9981. Min Act: -0.0003

Data Index: 1105968 (C4 (Web Text))

Max Activating Token Index: 205