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

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

Neuron 5906 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: 0.1877. Min Range: -0.1877

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1468268 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1710. Min Act: -0.0000

Data Index: 450841 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1795. Min Act: -0.0000

Data Index: 955891 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1050230 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1020323 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1500. Min Act: -0.0000

Data Index: 46550 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1146706 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1649911 (Python Code)

Max Activating Token Index: 481

Text #8

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1381. Min Act: -0.0000

Data Index: 82656 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1202511 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1361447 (Python Code)

Max Activating Token Index: 775

Text #11

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1346. Min Act: -0.0000

Data Index: 144384 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1541116 (Python Code)

Max Activating Token Index: 247

Text #13

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1333. Min Act: -0.0000

Data Index: 258284 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1456368 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1378193 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1271. Min Act: -0.0000

Data Index: 372987 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1387104 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1519161 (Python Code)

Max Activating Token Index: 680

Text #19

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1371711 (Python Code)

Max Activating Token Index: 304