Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1318 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1116806 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4242. Min Act: -0.0001

Data Index: 654578 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4493. Min Act: -0.0001

Data Index: 59278 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4087. Min Act: -0.0001

Data Index: 820141 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4652. Min Act: -0.0001

Data Index: 160558 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4331. Min Act: -0.0001

Data Index: 830462 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4611. Min Act: -0.0001

Data Index: 304262 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4446. Min Act: -0.0001

Data Index: 661413 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4441. Min Act: -0.0001

Data Index: 1244680 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4397. Min Act: -0.0001

Data Index: 428198 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4250. Min Act: -0.0001

Data Index: 166884 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4398. Min Act: -0.0001

Data Index: 215787 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4380. Min Act: -0.0001

Data Index: 102593 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4155. Min Act: -0.0001

Data Index: 830310 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4217. Min Act: -0.0001

Data Index: 257690 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4043. Min Act: -0.0001

Data Index: 663581 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4302. Min Act: -0.0001

Data Index: 1121093 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4394. Min Act: -0.0001

Data Index: 551190 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.4239. Min Act: -0.0001

Data Index: 336305 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.4800. Min Range: -0.4800

Max Act: 0.3941. Min Act: -0.0001

Data Index: 187544 (C4 (Web Text))

Max Activating Token Index: 851