Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2160 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1548. Min Act: -0.0001

Data Index: 431401 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1280766 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1275842 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1468. Min Act: -0.0001

Data Index: 97435 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1374. Min Act: -0.0001

Data Index: 30581 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1413. Min Act: -0.0001

Data Index: 400367 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1413. Min Act: -0.0001

Data Index: 299177 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1234016 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1239758 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1329. Min Act: -0.0001

Data Index: 133685 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1314. Min Act: -0.0001

Data Index: 156532 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1278095 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1334. Min Act: -0.0001

Data Index: 951282 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1306997 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1234. Min Act: -0.0001

Data Index: 649851 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1209. Min Act: -0.0001

Data Index: 965195 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1251. Min Act: -0.0001

Data Index: 961296 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1106772 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1243. Min Act: -0.0000

Data Index: 655058 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1128462 (C4 (Web Text))

Max Activating Token Index: 558