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

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

Neuron 830 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: 0.1649. Min Range: -0.1649

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1276440 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1649. Min Act: -0.0001

Data Index: 736198 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1568. Min Act: -0.0000

Data Index: 331903 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1515. Min Act: -0.0001

Data Index: 3485 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1504. Min Act: -0.0001

Data Index: 907119 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1100791 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1081945 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1418. Min Act: -0.0001

Data Index: 961628 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1225146 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1284195 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1465. Min Act: -0.0001

Data Index: 206351 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1409. Min Act: -0.0000

Data Index: 47233 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1240455 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1358. Min Act: -0.0001

Data Index: 977314 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1333. Min Act: -0.0000

Data Index: 639439 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1303077 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1296. Min Act: -0.0000

Data Index: 562060 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1244. Min Act: -0.0001

Data Index: 382966 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1348024 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1296. Min Act: -0.0000

Data Index: 950143 (C4 (Web Text))

Max Activating Token Index: 47