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

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

Neuron 3796 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: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0000

Data Index: 521354 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1766. Min Act: -0.0001

Data Index: 1252078 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1691. Min Act: -0.0001

Data Index: 627578 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1463160 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1486. Min Act: -0.0001

Data Index: 407238 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1478. Min Act: -0.0000

Data Index: 361865 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1335760 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1520. Min Act: -0.0000

Data Index: 754650 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1426. Min Act: 0.0001

Data Index: 616797 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1489. Min Act: -0.0000

Data Index: 565952 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1535116 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1405. Min Act: -0.0000

Data Index: 74764 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1440. Min Act: 0.0000

Data Index: 803741 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1489745 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1640745 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1388790 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1387. Min Act: -0.0000

Data Index: 377571 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1185767 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1472174 (Python Code)

Max Activating Token Index: 233