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

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

Neuron 1029 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0000

Data Index: 478542 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0463. Min Act: -0.0000

Data Index: 1399655 (Python Code)

Max Activating Token Index: 359

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1589614 (Python Code)

Max Activating Token Index: 409

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1483126 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0349. Min Act: -0.0000

Data Index: 734472 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0311. Min Act: -0.0000

Data Index: 1475333 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0322. Min Act: -0.0000

Data Index: 718362 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0346. Min Act: -0.0000

Data Index: 1480951 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1521683 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1405080 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1503020 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0294. Min Act: -0.0000

Data Index: 605826 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0324. Min Act: -0.0000

Data Index: 847259 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0332. Min Act: -0.0000

Data Index: 301723 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0350. Min Act: -0.0000

Data Index: 587399 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1584681 (Python Code)

Max Activating Token Index: 288

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1500983 (Python Code)

Max Activating Token Index: 600

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1446570 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1605988 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0291. Min Act: -0.0000

Data Index: 1612315 (Python Code)

Max Activating Token Index: 672