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

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

Neuron 1587 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.2365. Min Act: -0.0000

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1843. Min Act: -0.0000

Data Index: 639717 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1070. Min Act: -0.0001

Data Index: 563926 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1058980 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1215. Min Act: -0.0000

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1061366 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1453. Min Act: -0.0001

Data Index: 391905 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1284253 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1348. Min Act: -0.0000

Data Index: 1065571 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1346. Min Act: -0.0000

Data Index: 299721 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1459. Min Act: -0.0001

Data Index: 1057678 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1122739 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1002200 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0714. Min Act: -0.0000

Data Index: 172233 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0727. Min Act: -0.0000

Data Index: 812600 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0411. Min Act: -0.0000

Data Index: 519701 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0634. Min Act: -0.0000

Data Index: 248330 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1339747 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.1251. Min Act: -0.0000

Data Index: 978577 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 1.2365. Min Range: -1.2365

Max Act: 1.0947. Min Act: -0.0000

Data Index: 1078352 (C4 (Web Text))

Max Activating Token Index: 659