Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0419. Min Range: -2.0419

Max Act: 2.0419. Min Act: -0.0000

Data Index: 1147257 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.5746. Min Act: -0.0000

Data Index: 984664 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.6480. Min Act: -0.0000

Data Index: 680476 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.6343. Min Act: -0.0000

Data Index: 674739 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.5159. Min Act: -0.0000

Data Index: 841767 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.5105. Min Act: -0.0000

Data Index: 1109812 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4719. Min Act: -0.0000

Data Index: 348884 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4839. Min Act: -0.0000

Data Index: 1069320 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1107730 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4807. Min Act: -0.0000

Data Index: 991174 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4799. Min Act: -0.0000

Data Index: 236986 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4703. Min Act: -0.0000

Data Index: 772639 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4663. Min Act: -0.0000

Data Index: 221460 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4706. Min Act: -0.0000

Data Index: 364113 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4678. Min Act: -0.0000

Data Index: 913571 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4527. Min Act: -0.0000

Data Index: 520784 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4210. Min Act: -0.0000

Data Index: 1122488 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4028. Min Act: -0.0000

Data Index: 595214 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4544. Min Act: -0.0000

Data Index: 895399 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 2.0419. Min Range: -2.0419

Max Act: 1.4481. Min Act: -0.0000

Data Index: 956133 (C4 (Web Text))

Max Activating Token Index: 418