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

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

Neuron 1455 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2450. Min Act: -0.0000

Data Index: 39157 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1754. Min Act: -0.0000

Data Index: 693048 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1077357 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1672. Min Act: -0.0000

Data Index: 689287 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1090124 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1616. Min Act: -0.0001

Data Index: 392346 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1514. Min Act: -0.0000

Data Index: 174661 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1544. Min Act: -0.0000

Data Index: 915251 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1538. Min Act: -0.0000

Data Index: 327367 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1498. Min Act: -0.0000

Data Index: 844973 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1485. Min Act: -0.0001

Data Index: 922554 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1430. Min Act: -0.0001

Data Index: 539436 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1533. Min Act: -0.0000

Data Index: 752173 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1093380 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1428. Min Act: -0.0000

Data Index: 657786 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1411. Min Act: -0.0000

Data Index: 667790 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1437. Min Act: -0.0001

Data Index: 849545 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1374. Min Act: -0.0000

Data Index: 750797 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1378. Min Act: -0.0000

Data Index: 862115 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1298. Min Act: -0.0000

Data Index: 410539 (C4 (Web Text))

Max Activating Token Index: 850