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

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

Neuron 1461 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5019. Min Act: -0.0000

Data Index: 697617 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5424. Min Act: -0.0000

Data Index: 443268 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1218135 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5461. Min Act: -0.0000

Data Index: 88185 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1279668 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.5068. Min Act: -0.0000

Data Index: 169635 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4383. Min Act: -0.0000

Data Index: 458967 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4525. Min Act: -0.0000

Data Index: 183224 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1053327 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4421. Min Act: -0.0000

Data Index: 43791 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4362. Min Act: -0.0000

Data Index: 646951 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4434. Min Act: -0.0000

Data Index: 904053 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4419. Min Act: -0.0000

Data Index: 188484 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1135536 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4338. Min Act: -0.0000

Data Index: 426589 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4149. Min Act: -0.0000

Data Index: 732433 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4259. Min Act: -0.0000

Data Index: 362442 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.4367. Min Act: -0.0000

Data Index: 594403 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3972. Min Act: -0.0000

Data Index: 733797 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.5461. Min Range: -0.5461

Max Act: 0.3829. Min Act: -0.0000

Data Index: 563168 (C4 (Web Text))

Max Activating Token Index: 280