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

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

Neuron 5210 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.9508. Min Act: -0.0000

Data Index: 356887 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.6100. Min Act: -0.0000

Data Index: 275429 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.4676. Min Act: -0.0000

Data Index: 615831 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.7195. Min Act: -0.0000

Data Index: 1083238 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.3507. Min Act: -0.0000

Data Index: 550265 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.4727. Min Act: -0.0000

Data Index: 1159669 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.4219. Min Act: -0.0000

Data Index: 870535 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.5588. Min Act: -0.0000

Data Index: 156254 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.2590. Min Act: -0.0000

Data Index: 326806 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.2249. Min Act: -0.0000

Data Index: 1316672 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.1843. Min Act: -0.0000

Data Index: 1601864 (Python Code)

Max Activating Token Index: 503

Text #11

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.0353. Min Act: -0.0000

Data Index: 330158 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.1457. Min Act: -0.0000

Data Index: 1281849 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.0249. Min Act: -0.0000

Data Index: 144121 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.1089. Min Act: -0.0000

Data Index: 1129814 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 2.9508. Min Range: -2.9508

Max Act: 1.9920. Min Act: -0.0000

Data Index: 1237183 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.0492. Min Act: -0.0000

Data Index: 330766 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 2.9508. Min Range: -2.9508

Max Act: 2.0291. Min Act: -0.0000

Data Index: 1346779 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 2.9508. Min Range: -2.9508

Max Act: 1.9998. Min Act: -0.0000

Data Index: 293852 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 2.9508. Min Range: -2.9508

Max Act: 1.9974. Min Act: -0.0000

Data Index: 501624 (C4 (Web Text))

Max Activating Token Index: 486