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

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

Neuron 1090 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1536. Min Act: -0.0001

Data Index: 702842 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1561. Min Act: -0.0001

Data Index: 322053 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1426. Min Act: -0.0001

Data Index: 434446 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1417. Min Act: -0.0001

Data Index: 676098 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1371. Min Act: -0.0001

Data Index: 725977 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1401. Min Act: -0.0001

Data Index: 620838 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1383. Min Act: -0.0001

Data Index: 493649 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1366. Min Act: -0.0001

Data Index: 906403 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1336. Min Act: -0.0001

Data Index: 18316 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1419. Min Act: -0.0001

Data Index: 612931 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1398. Min Act: -0.0001

Data Index: 296072 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1318. Min Act: -0.0001

Data Index: 562322 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1323. Min Act: -0.0001

Data Index: 149733 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1353. Min Act: -0.0001

Data Index: 152696 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1302. Min Act: -0.0001

Data Index: 999169 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1015692 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1001177 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1279. Min Act: -0.0001

Data Index: 949671 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1314. Min Act: -0.0000

Data Index: 139061 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1298. Min Act: -0.0001

Data Index: 558110 (C4 (Web Text))

Max Activating Token Index: 679