Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.2334. Min Act: -0.0000

Data Index: 235772 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1242750 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1538. Min Act: -0.0001

Data Index: 255824 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1252205 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1458. Min Act: -0.0000

Data Index: 955046 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1457. Min Act: -0.0001

Data Index: 481460 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1278. Min Act: -0.0001

Data Index: 671904 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1414. Min Act: -0.0000

Data Index: 801172 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1350. Min Act: -0.0000

Data Index: 742435 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1225274 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1193465 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1289. Min Act: -0.0000

Data Index: 620859 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1336. Min Act: -0.0000

Data Index: 38667 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1336. Min Act: -0.0000

Data Index: 588019 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1363. Min Act: -0.0000

Data Index: 804335 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1211. Min Act: -0.0000

Data Index: 43264 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1323353 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1108398 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1237. Min Act: -0.0000

Data Index: 476755 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.2334. Min Range: -0.2334

Max Act: 0.1283. Min Act: -0.0000

Data Index: 429872 (C4 (Web Text))

Max Activating Token Index: 52