Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.3592. Min Act: -0.0000

Data Index: 496661 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.4613. Min Act: -0.0000

Data Index: 818103 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.1260. Min Act: -0.0000

Data Index: 913160 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.1784. Min Act: -0.0000

Data Index: 218777 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.2901. Min Act: -0.0000

Data Index: 356628 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.0490. Min Act: -0.0000

Data Index: 283377 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.2561. Min Act: -0.0000

Data Index: 676364 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.1256. Min Act: -0.0000

Data Index: 865428 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.1290. Min Act: -0.0000

Data Index: 506468 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.9875. Min Act: -0.0000

Data Index: 537293 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.1044. Min Act: -0.0000

Data Index: 873116 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.0701. Min Act: -0.0000

Data Index: 1197971 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.0547. Min Act: -0.0000

Data Index: 763738 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.9411. Min Act: -0.0000

Data Index: 268820 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 2.4613. Min Range: -2.4613

Max Act: 1.9286. Min Act: -0.0000

Data Index: 918167 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.0281. Min Act: -0.0000

Data Index: 417147 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.0260. Min Act: -0.0000

Data Index: 62127 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.0290. Min Act: -0.0000

Data Index: 632781 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.0200. Min Act: -0.0000

Data Index: 740231 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 2.4613. Min Range: -2.4613

Max Act: 2.0137. Min Act: -0.0000

Data Index: 286741 (C4 (Web Text))

Max Activating Token Index: 980