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

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

Neuron 1104 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1446. Min Act: -0.0001

Data Index: 100871 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1148401 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1293. Min Act: -0.0001

Data Index: 517053 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1407. Min Act: -0.0001

Data Index: 887914 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1227138 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1265. Min Act: -0.0001

Data Index: 205952 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1299. Min Act: -0.0001

Data Index: 427682 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1229. Min Act: -0.0001

Data Index: 768439 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1184. Min Act: -0.0001

Data Index: 107426 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1363. Min Act: -0.0001

Data Index: 445732 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1254. Min Act: -0.0001

Data Index: 686220 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1170323 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1266. Min Act: -0.0001

Data Index: 345415 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1249. Min Act: -0.0001

Data Index: 30781 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1304. Min Act: -0.0001

Data Index: 825838 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1252. Min Act: -0.0001

Data Index: 569225 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1149068 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1198. Min Act: -0.0001

Data Index: 785844 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1276. Min Act: -0.0001

Data Index: 858805 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1051047 (C4 (Web Text))

Max Activating Token Index: 817