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

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

Neuron 3506 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1740. Min Act: -0.0000

Data Index: 207363 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1156072 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0000

Data Index: 2126 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1340643 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1518. Min Act: -0.0000

Data Index: 223236 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1495. Min Act: -0.0000

Data Index: 872258 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1448. Min Act: -0.0000

Data Index: 799437 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1435. Min Act: -0.0000

Data Index: 708183 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1374. Min Act: -0.0001

Data Index: 123870 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1451. Min Act: -0.0000

Data Index: 987258 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1414. Min Act: -0.0001

Data Index: 1195817 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1559. Min Act: -0.0001

Data Index: 438476 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1015643 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1396. Min Act: -0.0000

Data Index: 930362 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1384. Min Act: -0.0000

Data Index: 386062 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1026510 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1363. Min Act: -0.0000

Data Index: 739484 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1363. Min Act: -0.0000

Data Index: 295078 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1264. Min Act: -0.0001

Data Index: 477545 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1129. Min Act: -0.0001

Data Index: 807059 (C4 (Web Text))

Max Activating Token Index: 707