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

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

Neuron 5602 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.4393. Min Act: -0.0000

Data Index: 697616 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.5711. Min Act: -0.0000

Data Index: 368149 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.2773. Min Act: -0.0000

Data Index: 604875 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.1465. Min Act: -0.0000

Data Index: 254696 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.1375. Min Act: -0.0000

Data Index: 706788 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.1293. Min Act: 0.0000

Data Index: 1257855 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.1324. Min Act: -0.0000

Data Index: 827224 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1181422 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.5711. Min Range: -1.5711

Max Act: 1.0752. Min Act: -0.0000

Data Index: 541015 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1134601 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.9778. Min Act: -0.0000

Data Index: 172499 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.9201. Min Act: -0.0000

Data Index: 575468 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.9257. Min Act: -0.0000

Data Index: 788030 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.8643. Min Act: -0.0000

Data Index: 259581 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.9037. Min Act: -0.0000

Data Index: 705750 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1232089 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.8951. Min Act: -0.0000

Data Index: 181870 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.8334. Min Act: -0.0000

Data Index: 246331 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.8691. Min Act: -0.0000

Data Index: 364329 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.5711. Min Range: -1.5711

Max Act: 0.8202. Min Act: -0.0000

Data Index: 719476 (C4 (Web Text))

Max Activating Token Index: 620