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

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

Neuron 960 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2645. Min Act: -0.0001

Data Index: 14016 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1849. Min Act: -0.0001

Data Index: 165306 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1989. Min Act: -0.0001

Data Index: 509319 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1566. Min Act: -0.0001

Data Index: 913923 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1617. Min Act: -0.0001

Data Index: 943410 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1254851 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1609. Min Act: -0.0001

Data Index: 92813 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1581. Min Act: -0.0001

Data Index: 623480 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1513. Min Act: -0.0001

Data Index: 188505 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1405. Min Act: -0.0001

Data Index: 750512 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1095180 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1537. Min Act: -0.0001

Data Index: 19913 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1505. Min Act: -0.0001

Data Index: 807819 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1514. Min Act: -0.0001

Data Index: 982041 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1141377 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1503. Min Act: -0.0001

Data Index: 841690 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1386. Min Act: -0.0001

Data Index: 132932 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1236. Min Act: -0.0001

Data Index: 931627 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1519. Min Act: -0.0001

Data Index: 759312 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1274186 (C4 (Web Text))

Max Activating Token Index: 394