Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1521 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1553. Min Act: -0.0004

Data Index: 238700 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1559. Min Act: -0.0003

Data Index: 853832 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1457. Min Act: -0.0003

Data Index: 972552 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1470. Min Act: -0.0003

Data Index: 1344860 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1383. Min Act: -0.0003

Data Index: 897979 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1411. Min Act: -0.0003

Data Index: 796521 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1502. Min Act: -0.0003

Data Index: 793067 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1388. Min Act: -0.0003

Data Index: 959544 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1458. Min Act: -0.0003

Data Index: 502358 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1484. Min Act: -0.0003

Data Index: 859588 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1430. Min Act: -0.0003

Data Index: 440898 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1459. Min Act: -0.0003

Data Index: 329612 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1331. Min Act: -0.0003

Data Index: 527448 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1399. Min Act: -0.0003

Data Index: 840196 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1396. Min Act: -0.0003

Data Index: 1175195 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1372. Min Act: -0.0003

Data Index: 1222314 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1419. Min Act: -0.0003

Data Index: 436431 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1417. Min Act: -0.0003

Data Index: 91442 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1347. Min Act: -0.0004

Data Index: 1329503 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1283. Min Act: -0.0004

Data Index: 1024116 (C4 (Web Text))

Max Activating Token Index: 836