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

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

Neuron 1275 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: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0001

Data Index: 72706 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1323848 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1507. Min Act: -0.0001

Data Index: 123075 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1495. Min Act: -0.0001

Data Index: 646699 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1659. Min Act: -0.0001

Data Index: 430047 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1523. Min Act: -0.0001

Data Index: 286701 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1483. Min Act: -0.0001

Data Index: 432165 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1507. Min Act: -0.0001

Data Index: 345416 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1442. Min Act: -0.0001

Data Index: 541472 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1231. Min Act: -0.0001

Data Index: 966775 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1277. Min Act: -0.0001

Data Index: 774805 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1172. Min Act: -0.0001

Data Index: 327840 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1221. Min Act: -0.0001

Data Index: 100324 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1277. Min Act: -0.0001

Data Index: 475239 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1218. Min Act: -0.0001

Data Index: 805623 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1198. Min Act: -0.0001

Data Index: 958131 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1306. Min Act: -0.0001

Data Index: 801246 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1164. Min Act: -0.0001

Data Index: 407116 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1255. Min Act: -0.0001

Data Index: 260922 (C4 (Web Text))

Max Activating Token Index: 474