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

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

Neuron 977 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: 0.1662. Min Range: -0.1662

Max Act: 0.1642. Min Act: -0.0001

Data Index: 368957 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1288989 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1645. Min Act: -0.0001

Data Index: 270824 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1171829 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1459. Min Act: -0.0001

Data Index: 862190 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1353. Min Act: -0.0000

Data Index: 400533 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1476. Min Act: -0.0001

Data Index: 179206 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1350. Min Act: -0.0001

Data Index: 205321 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1445. Min Act: -0.0000

Data Index: 925454 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1251358 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1487. Min Act: -0.0001

Data Index: 864906 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1435. Min Act: -0.0001

Data Index: 500826 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1434. Min Act: -0.0000

Data Index: 216372 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1158862 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1467. Min Act: -0.0001

Data Index: 820936 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1187592 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1096956 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1425. Min Act: -0.0000

Data Index: 142849 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1452. Min Act: -0.0000

Data Index: 633752 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1308. Min Act: -0.0001

Data Index: 90209 (C4 (Web Text))

Max Activating Token Index: 703