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

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

Neuron 3964 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7761. Min Act: -0.0001

Data Index: 573919 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.6091. Min Act: -0.0001

Data Index: 1207409 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.2158. Min Act: -0.0001

Data Index: 957915 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.2345. Min Act: -0.0001

Data Index: 1118258 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1761. Min Act: -0.0001

Data Index: 106189 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1650. Min Act: -0.0001

Data Index: 738630 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1347. Min Act: -0.0001

Data Index: 535293 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1346. Min Act: -0.0001

Data Index: 578378 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1351. Min Act: -0.0001

Data Index: 803665 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1621. Min Act: -0.0001

Data Index: 1189919 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.0328. Min Act: -0.0001

Data Index: 706245 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1246. Min Act: -0.0001

Data Index: 591040 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1855. Min Act: -0.0001

Data Index: 1189599 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.0892. Min Act: -0.0001

Data Index: 484418 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1053. Min Act: -0.0001

Data Index: 1138766 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1270. Min Act: -0.0001

Data Index: 385772 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.0970. Min Act: -0.0001

Data Index: 1289775 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1013. Min Act: -0.0001

Data Index: 514662 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.0200. Min Act: -0.0001

Data Index: 540792 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.2123. Min Act: -0.0001

Data Index: 1284343 (C4 (Web Text))

Max Activating Token Index: 716