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

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

Neuron 4019 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: 0.1539. Min Range: -0.1539

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1326674 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1480. Min Act: -0.0000

Data Index: 398146 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1466. Min Act: -0.0000

Data Index: 299428 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1539. Min Act: -0.0001

Data Index: 882278 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1221639 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1210089 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1505. Min Act: -0.0001

Data Index: 574092 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1461. Min Act: -0.0001

Data Index: 466689 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1421. Min Act: -0.0001

Data Index: 355977 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1416. Min Act: -0.0001

Data Index: 4234 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1206942 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1416. Min Act: -0.0001

Data Index: 684220 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1048 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1343406 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1275. Min Act: -0.0001

Data Index: 304127 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1310. Min Act: -0.0000

Data Index: 571158 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1241. Min Act: -0.0000

Data Index: 218895 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1363. Min Act: -0.0001

Data Index: 816210 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1265. Min Act: -0.0000

Data Index: 710532 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1261. Min Act: -0.0000

Data Index: 580440 (C4 (Web Text))

Max Activating Token Index: 313