Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3357 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1263873 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1305447 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1096743 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1812. Min Act: -0.0000

Data Index: 246940 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1742. Min Act: -0.0000

Data Index: 167359 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1707. Min Act: -0.0000

Data Index: 165862 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1627. Min Act: -0.0000

Data Index: 133500 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1632856 (Python Code)

Max Activating Token Index: 661

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1682. Min Act: -0.0000

Data Index: 893203 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1629. Min Act: -0.0000

Data Index: 58066 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1401589 (Python Code)

Max Activating Token Index: 483

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1567506 (Python Code)

Max Activating Token Index: 344

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1448199 (Python Code)

Max Activating Token Index: 498

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1604350 (Python Code)

Max Activating Token Index: 246

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1538. Min Act: -0.0000

Data Index: 856220 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1326361 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1640037 (Python Code)

Max Activating Token Index: 118

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1593029 (Python Code)

Max Activating Token Index: 441

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1571407 (Python Code)

Max Activating Token Index: 461