Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 34 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0001

Data Index: 101357 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0657. Min Act: -0.0001

Data Index: 441852 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0679. Min Act: -0.0002

Data Index: 433456 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0652. Min Act: -0.0001

Data Index: 730508 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0646. Min Act: -0.0002

Data Index: 26070 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1465630 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1556048 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0599. Min Act: -0.0001

Data Index: 971211 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1040240 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1451892 (Python Code)

Max Activating Token Index: 861

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1476657 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0557. Min Act: -0.0001

Data Index: 23162 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1288368 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0537. Min Act: -0.0001

Data Index: 913370 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1382804 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1032768 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1445739 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1320555 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1578976 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0440. Min Act: -0.0001

Data Index: 781974 (C4 (Web Text))

Max Activating Token Index: 838