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

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

Neuron 1733 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: 0.7551. Min Range: -0.7551

Max Act: 0.7551. Min Act: -0.0000

Data Index: 687789 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1247516 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6076. Min Act: 0.0001

Data Index: 1203256 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1398039 (Python Code)

Max Activating Token Index: 608

Text #4

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5225. Min Act: 0.0001

Data Index: 3420 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5345. Min Act: -0.0000

Data Index: 966471 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4983. Min Act: -0.0000

Data Index: 652418 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4921. Min Act: -0.0000

Data Index: 605523 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4855. Min Act: -0.0000

Data Index: 542440 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1416293 (Python Code)

Max Activating Token Index: 435

Text #10

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4788. Min Act: -0.0000

Data Index: 663783 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4386. Min Act: 0.0000

Data Index: 1066821 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1096508 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4680. Min Act: -0.0000

Data Index: 617127 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1329241 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4338. Min Act: -0.0000

Data Index: 45580 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1492387 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4360. Min Act: 0.0000

Data Index: 990061 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4246. Min Act: -0.0000

Data Index: 652468 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.4210. Min Act: 0.0001

Data Index: 209371 (C4 (Web Text))

Max Activating Token Index: 262