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

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

Neuron 3476 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1043107 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1671. Min Act: -0.0001

Data Index: 857917 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1634. Min Act: -0.0001

Data Index: 933608 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1232724 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1621. Min Act: -0.0001

Data Index: 939709 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1546. Min Act: -0.0001

Data Index: 667220 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1182029 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1294718 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1445. Min Act: -0.0001

Data Index: 605623 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1559. Min Act: -0.0001

Data Index: 854410 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1425. Min Act: -0.0001

Data Index: 540843 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1421. Min Act: -0.0001

Data Index: 789149 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1581. Min Act: -0.0001

Data Index: 927008 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1098136 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1626. Min Act: -0.0001

Data Index: 438122 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1564. Min Act: -0.0001

Data Index: 927498 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1499. Min Act: -0.0001

Data Index: 20938 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1444. Min Act: -0.0001

Data Index: 28631 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1539. Min Act: -0.0001

Data Index: 335341 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1386. Min Act: -0.0001

Data Index: 72334 (C4 (Web Text))

Max Activating Token Index: 374