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

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

Neuron 3425 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: 0.1698. Min Range: -0.1698

Max Act: 0.1698. Min Act: -0.0000

Data Index: 197207 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1183947 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1063169 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1466. Min Act: -0.0000

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1412. Min Act: -0.0000

Data Index: 916029 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1387. Min Act: -0.0000

Data Index: 340624 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1397. Min Act: -0.0000

Data Index: 473177 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1470. Min Act: -0.0000

Data Index: 715892 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1329631 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1382. Min Act: -0.0000

Data Index: 886596 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1267. Min Act: -0.0000

Data Index: 888212 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1155118 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1347. Min Act: -0.0000

Data Index: 821699 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1246. Min Act: -0.0000

Data Index: 88622 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1301. Min Act: -0.0000

Data Index: 976179 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1255. Min Act: -0.0000

Data Index: 789260 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1233. Min Act: -0.0000

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1337. Min Act: -0.0000

Data Index: 334519 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1244. Min Act: -0.0000

Data Index: 186636 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1282. Min Act: -0.0000

Data Index: 966172 (C4 (Web Text))

Max Activating Token Index: 73