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

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

Neuron 1800 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1225483 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2054. Min Act: -0.0001

Data Index: 333483 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1306082 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1855. Min Act: 0.0000

Data Index: 211525 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1790. Min Act: -0.0001

Data Index: 559938 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1724. Min Act: -0.0001

Data Index: 373644 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1674. Min Act: -0.0001

Data Index: 516960 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1622. Min Act: -0.0001

Data Index: 425832 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1644. Min Act: -0.0001

Data Index: 838212 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1645. Min Act: -0.0001

Data Index: 794277 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1614. Min Act: -0.0001

Data Index: 174596 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1604. Min Act: -0.0001

Data Index: 601607 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1520. Min Act: -0.0001

Data Index: 513048 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1286426 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1566. Min Act: -0.0001

Data Index: 462493 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1610. Min Act: -0.0001

Data Index: 282060 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1484. Min Act: -0.0001

Data Index: 87235 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1484. Min Act: -0.0001

Data Index: 16610 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1580. Min Act: -0.0001

Data Index: 740221 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1469. Min Act: -0.0001

Data Index: 266855 (C4 (Web Text))

Max Activating Token Index: 555