Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 666 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0002

Data Index: 221604 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0463. Min Act: -0.0002

Data Index: 674083 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0432. Min Act: -0.0002

Data Index: 302552 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0424. Min Act: -0.0002

Data Index: 509384 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0402. Min Act: -0.0002

Data Index: 374258 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0401. Min Act: -0.0002

Data Index: 861725 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0398. Min Act: -0.0002

Data Index: 564118 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1121231 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0408. Min Act: -0.0002

Data Index: 330407 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0386. Min Act: -0.0002

Data Index: 157143 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0385. Min Act: -0.0002

Data Index: 625578 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0375. Min Act: -0.0002

Data Index: 204521 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0383. Min Act: -0.0002

Data Index: 968363 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0378. Min Act: -0.0002

Data Index: 928365 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0374. Min Act: -0.0002

Data Index: 613467 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0376. Min Act: -0.0002

Data Index: 696428 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0374. Min Act: -0.0002

Data Index: 820307 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0374. Min Act: -0.0001

Data Index: 97085 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0370. Min Act: -0.0002

Data Index: 448338 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1202457 (C4 (Web Text))

Max Activating Token Index: 1011