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

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

Neuron 3052 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: 0.1809. Min Range: -0.1809

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1098927 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1276193 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1699. Min Act: -0.0001

Data Index: 764510 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1480. Min Act: -0.0001

Data Index: 480292 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1630. Min Act: -0.0001

Data Index: 727307 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1105592 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1611. Min Act: -0.0001

Data Index: 102998 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1597. Min Act: -0.0001

Data Index: 705351 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1555. Min Act: -0.0001

Data Index: 64357 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1440. Min Act: -0.0001

Data Index: 65473 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1550. Min Act: -0.0001

Data Index: 74224 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1180713 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1360. Min Act: -0.0001

Data Index: 11490 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1467. Min Act: -0.0001

Data Index: 786187 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1463. Min Act: -0.0001

Data Index: 922686 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1570. Min Act: -0.0001

Data Index: 655475 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1206. Min Act: -0.0001

Data Index: 279367 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1265. Min Act: -0.0001

Data Index: 932944 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1106. Min Act: -0.0001

Data Index: 763374 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.1809. Min Range: -0.1809

Max Act: 0.1244. Min Act: -0.0001

Data Index: 467018 (C4 (Web Text))

Max Activating Token Index: 941