Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1290 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1180869 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1813. Min Act: -0.0001

Data Index: 999949 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1128678 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1035965 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1555. Min Act: -0.0001

Data Index: 512010 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1628. Min Act: -0.0001

Data Index: 893539 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1321196 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1268602 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1483. Min Act: -0.0001

Data Index: 185048 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1408. Min Act: -0.0001

Data Index: 203208 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1071971 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1329. Min Act: -0.0001

Data Index: 421714 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1411. Min Act: -0.0001

Data Index: 509695 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1404. Min Act: -0.0001

Data Index: 586028 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1392. Min Act: -0.0001

Data Index: 743168 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1410. Min Act: -0.0001

Data Index: 626163 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1352. Min Act: -0.0001

Data Index: 99230 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1340. Min Act: -0.0001

Data Index: 850563 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1260. Min Act: -0.0001

Data Index: 920109 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1291. Min Act: -0.0001

Data Index: 941727 (C4 (Web Text))

Max Activating Token Index: 401