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

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

Neuron 2092 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1694. Min Act: -0.0001

Data Index: 198429 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1600. Min Act: -0.0001

Data Index: 719320 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1650997 (Python Code)

Max Activating Token Index: 353

Text #3

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1251036 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1180864 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1451. Min Act: -0.0001

Data Index: 457344 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1023558 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1155 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1342857 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1230. Min Act: -0.0001

Data Index: 972417 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1444. Min Act: -0.0000

Data Index: 676540 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1499708 (Python Code)

Max Activating Token Index: 697

Text #12

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1209332 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1348. Min Act: -0.0001

Data Index: 540145 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1029639 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1254. Min Act: -0.0001

Data Index: 868104 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1308. Min Act: -0.0001

Data Index: 8286 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1452337 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1212. Min Act: -0.0001

Data Index: 479422 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1464548 (Python Code)

Max Activating Token Index: 246