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

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

Neuron 983 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: 0.1566. Min Range: -0.1566

Max Act: 0.1517. Min Act: -0.0001

Data Index: 135388 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1566. Min Act: -0.0001

Data Index: 957452 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1449. Min Act: -0.0001

Data Index: 361155 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1467. Min Act: -0.0001

Data Index: 855042 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1391. Min Act: -0.0001

Data Index: 766268 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1409. Min Act: -0.0001

Data Index: 158963 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1396. Min Act: -0.0001

Data Index: 732013 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1098365 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1343. Min Act: -0.0001

Data Index: 460308 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1421. Min Act: -0.0001

Data Index: 797161 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1371. Min Act: -0.0001

Data Index: 306935 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1407. Min Act: -0.0001

Data Index: 380361 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1344. Min Act: -0.0001

Data Index: 211180 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1331. Min Act: -0.0001

Data Index: 503153 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1298. Min Act: -0.0001

Data Index: 556041 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1262. Min Act: -0.0001

Data Index: 926392 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1246. Min Act: -0.0001

Data Index: 913511 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1329. Min Act: -0.0001

Data Index: 686794 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1319. Min Act: -0.0001

Data Index: 231180 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1354169 (C4 (Web Text))

Max Activating Token Index: 383