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

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

Neuron 2188 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1608. Min Act: -0.0000

Data Index: 31585 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1285911 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1587. Min Act: -0.0000

Data Index: 723225 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1339030 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1443. Min Act: -0.0000

Data Index: 54785 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1386. Min Act: -0.0000

Data Index: 860833 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1467. Min Act: -0.0000

Data Index: 177872 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1418. Min Act: -0.0000

Data Index: 529721 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1415. Min Act: -0.0000

Data Index: 260218 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1467. Min Act: -0.0000

Data Index: 114972 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1459. Min Act: -0.0000

Data Index: 31388 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1075561 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1194264 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1335. Min Act: -0.0000

Data Index: 735563 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1379. Min Act: -0.0000

Data Index: 358551 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1281. Min Act: -0.0000

Data Index: 618800 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1325. Min Act: -0.0000

Data Index: 204386 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1277135 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1270. Min Act: -0.0000

Data Index: 463676 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1319. Min Act: -0.0000

Data Index: 630130 (C4 (Web Text))

Max Activating Token Index: 552