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

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

Neuron 5972 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.3343. Min Act: 0.0001

Data Index: 333437 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1126647 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.2585. Min Act: -0.0000

Data Index: 258453 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1485709 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.1488. Min Act: -0.0000

Data Index: 1136239 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1369473 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.2135. Min Act: -0.0000

Data Index: 95964 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1319232 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0726. Min Act: -0.0000

Data Index: 1285937 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0944. Min Act: -0.0000

Data Index: 234748 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0902. Min Act: 0.0000

Data Index: 821716 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1312976 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1120690 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0230. Min Act: -0.0000

Data Index: 137478 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0219. Min Act: -0.0000

Data Index: 469254 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0708. Min Act: -0.0000

Data Index: 984566 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0307. Min Act: -0.0000

Data Index: 187272 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1066758 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0410. Min Act: 0.0000

Data Index: 1286957 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.3343. Min Range: -1.3343

Max Act: 1.0175. Min Act: -0.0000

Data Index: 64604 (C4 (Web Text))

Max Activating Token Index: 247