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

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

Neuron 2 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1773. Min Act: -0.0001

Data Index: 696032 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1626. Min Act: -0.0001

Data Index: 148903 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1569. Min Act: -0.0001

Data Index: 8372 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1561. Min Act: -0.0001

Data Index: 812064 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1591. Min Act: -0.0001

Data Index: 222536 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1521. Min Act: -0.0001

Data Index: 516945 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1142115 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1154952 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1284386 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1269566 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1339. Min Act: -0.0001

Data Index: 121703 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1145716 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1326. Min Act: -0.0001

Data Index: 627396 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1335. Min Act: -0.0001

Data Index: 474953 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1374. Min Act: -0.0001

Data Index: 543020 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1273. Min Act: -0.0001

Data Index: 989217 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1214525 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1367. Min Act: -0.0001

Data Index: 158520 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1299. Min Act: -0.0001

Data Index: 536585 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1085355 (C4 (Web Text))

Max Activating Token Index: 161