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

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

Neuron 1476 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1257146 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1276. Min Act: -0.0001

Data Index: 164591 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1478071 (Python Code)

Max Activating Token Index: 610

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1351. Min Act: -0.0000

Data Index: 965007 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1372. Min Act: -0.0000

Data Index: 716234 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1367. Min Act: -0.0001

Data Index: 684902 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1358. Min Act: -0.0000

Data Index: 546417 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1252111 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1229664 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1096030 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1219. Min Act: -0.0000

Data Index: 707369 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1129. Min Act: -0.0000

Data Index: 733713 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1165. Min Act: -0.0000

Data Index: 803982 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1203. Min Act: -0.0000

Data Index: 986685 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1145. Min Act: -0.0000

Data Index: 810782 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1147. Min Act: -0.0000

Data Index: 855796 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1018152 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1197491 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1198930 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.0977. Min Act: -0.0000

Data Index: 438157 (C4 (Web Text))

Max Activating Token Index: 334