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

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

Neuron 131 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: 0.1728. Min Range: -0.1728

Max Act: 0.1630. Min Act: -0.0001

Data Index: 732260 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1558. Min Act: -0.0001

Data Index: 667940 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1422. Min Act: -0.0001

Data Index: 437298 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1236386 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1201388 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1450. Min Act: -0.0001

Data Index: 398394 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1079705 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1615468 (Python Code)

Max Activating Token Index: 300

Text #8

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1305. Min Act: -0.0001

Data Index: 943156 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1313. Min Act: -0.0001

Data Index: 695699 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1246. Min Act: -0.0001

Data Index: 781308 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1146211 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1303. Min Act: -0.0001

Data Index: 118587 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1346529 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1426243 (Python Code)

Max Activating Token Index: 877

Text #15

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1420219 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1121. Min Act: -0.0001

Data Index: 894761 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1211. Min Act: -0.0001

Data Index: 294515 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1063. Min Act: -0.0001

Data Index: 159863 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1132. Min Act: -0.0001

Data Index: 337613 (C4 (Web Text))

Max Activating Token Index: 646