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

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

Neuron 2557 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: 0.1665. Min Range: -0.1665

Max Act: 0.1665. Min Act: -0.0000

Data Index: 117120 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1510. Min Act: -0.0001

Data Index: 459308 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1523. Min Act: -0.0000

Data Index: 420526 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1462. Min Act: -0.0000

Data Index: 469337 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1403. Min Act: -0.0001

Data Index: 841431 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1406. Min Act: -0.0000

Data Index: 312334 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1416. Min Act: -0.0000

Data Index: 458593 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1167225 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1310976 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1319654 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1283. Min Act: -0.0000

Data Index: 545065 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1321. Min Act: -0.0000

Data Index: 310658 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1227. Min Act: -0.0000

Data Index: 497299 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1353. Min Act: -0.0000

Data Index: 980754 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1354. Min Act: -0.0001

Data Index: 54057 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1291. Min Act: -0.0000

Data Index: 231912 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1243. Min Act: -0.0000

Data Index: 201231 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1212240 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1260. Min Act: -0.0000

Data Index: 233596 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1215. Min Act: -0.0000

Data Index: 174889 (C4 (Web Text))

Max Activating Token Index: 94