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

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

Neuron 2516 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1989. Min Act: -0.0000

Data Index: 353896 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1545888 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1554. Min Act: -0.0000

Data Index: 249376 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1582652 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1070848 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1503. Min Act: -0.0000

Data Index: 159679 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1455. Min Act: -0.0000

Data Index: 407262 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1487. Min Act: -0.0000

Data Index: 980842 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1364. Min Act: -0.0000

Data Index: 808030 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1420. Min Act: -0.0000

Data Index: 868293 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1381. Min Act: -0.0000

Data Index: 419135 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1413. Min Act: -0.0000

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1577354 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1022914 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1422. Min Act: -0.0000

Data Index: 142182 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1284. Min Act: -0.0000

Data Index: 235938 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1378. Min Act: -0.0000

Data Index: 503424 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1593834 (Python Code)

Max Activating Token Index: 833

Text #18

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1087575 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.1989. Min Range: -0.1989

Max Act: 0.1277. Min Act: -0.0000

Data Index: 159332 (C4 (Web Text))

Max Activating Token Index: 774