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

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

Neuron 5321 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1696. Min Act: -0.0001

Data Index: 826311 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1689. Min Act: -0.0001

Data Index: 334741 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1115019 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1534. Min Act: -0.0001

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1467. Min Act: -0.0001

Data Index: 815240 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1542. Min Act: -0.0001

Data Index: 397184 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1477. Min Act: -0.0001

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1640. Min Act: -0.0001

Data Index: 456313 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1547. Min Act: -0.0001

Data Index: 1077169 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1467. Min Act: -0.0001

Data Index: 743143 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1304. Min Act: -0.0001

Data Index: 429327 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1345. Min Act: -0.0001

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1452. Min Act: -0.0001

Data Index: 478527 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1404. Min Act: -0.0001

Data Index: 995094 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1314. Min Act: -0.0001

Data Index: 312117 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1333. Min Act: -0.0001

Data Index: 235633 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1252. Min Act: -0.0001

Data Index: 706948 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1028748 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1217. Min Act: -0.0001

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 436