Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3241 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2310. Min Range: -2.2310

Max Act: 2.2310. Min Act: -0.0000

Data Index: 267848 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.7359. Min Act: -0.0000

Data Index: 305960 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.6804. Min Act: -0.0000

Data Index: 1188440 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.6296. Min Act: -0.0000

Data Index: 258714 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.6457. Min Act: -0.0000

Data Index: 84916 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.6087. Min Act: -0.0000

Data Index: 408566 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.5858. Min Act: -0.0000

Data Index: 21682 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.6156. Min Act: -0.0000

Data Index: 786278 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.5385. Min Act: -0.0000

Data Index: 267004 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.5332. Min Act: -0.0000

Data Index: 313618 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.5359. Min Act: -0.0000

Data Index: 1032548 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.4532. Min Act: -0.0000

Data Index: 448835 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.5692. Min Act: -0.0000

Data Index: 381738 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.4391. Min Act: -0.0000

Data Index: 891052 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.4743. Min Act: -0.0000

Data Index: 380783 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.6287. Min Act: -0.0000

Data Index: 229501 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.5103. Min Act: -0.0000

Data Index: 338165 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.4541. Min Act: -0.0000

Data Index: 143326 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.5541. Min Act: -0.0000

Data Index: 263755 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 2.2310. Min Range: -2.2310

Max Act: 1.5438. Min Act: -0.0000

Data Index: 583888 (C4 (Web Text))

Max Activating Token Index: 37