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

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

Neuron 714 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: 0.1873. Min Range: -0.1873

Max Act: 0.1873. Min Act: -0.0001

Data Index: 327136 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1552. Min Act: -0.0001

Data Index: 754348 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1651. Min Act: -0.0001

Data Index: 107596 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1008255 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1061793 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1085781 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1212526 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1431. Min Act: -0.0001

Data Index: 738814 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1466. Min Act: -0.0001

Data Index: 423479 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1376. Min Act: -0.0001

Data Index: 291562 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1369. Min Act: -0.0001

Data Index: 126241 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1297. Min Act: -0.0001

Data Index: 205463 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1141500 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1277702 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1256451 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1395. Min Act: -0.0001

Data Index: 934542 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1241. Min Act: -0.0001

Data Index: 32745 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1334. Min Act: -0.0001

Data Index: 643105 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1213191 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1315. Min Act: -0.0001

Data Index: 760314 (C4 (Web Text))

Max Activating Token Index: 35