Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2359 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1526833 (Python Code)

Max Activating Token Index: 799

Text #1

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1484679 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4250. Min Act: -0.0000

Data Index: 958374 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3839. Min Act: 0.0000

Data Index: 644399 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4168. Min Act: -0.0000

Data Index: 887394 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1648462 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1367618 (Python Code)

Max Activating Token Index: 942

Text #7

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1394112 (Python Code)

Max Activating Token Index: 804

Text #8

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1330996 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1580201 (Python Code)

Max Activating Token Index: 516

Text #10

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1647894 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1534283 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1551982 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1600742 (Python Code)

Max Activating Token Index: 557

Text #14

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3393. Min Act: 0.0000

Data Index: 1378186 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3472. Min Act: -0.0000

Data Index: 519105 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1403399 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1507964 (Python Code)

Max Activating Token Index: 199

Text #18

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3270. Min Act: -0.0000

Data Index: 515472 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.4789. Min Range: -0.4789

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1559408 (Python Code)

Max Activating Token Index: 593