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

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

Neuron 5604 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: 0.2089. Min Range: -0.2089

Max Act: 0.2089. Min Act: -0.0001

Data Index: 528684 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1888. Min Act: -0.0001

Data Index: 794524 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1572391 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1396695 (Python Code)

Max Activating Token Index: 952

Text #4

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1651735 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1452685 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1692. Min Act: -0.0001

Data Index: 571929 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1263. Min Act: -0.0001

Data Index: 348334 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1439652 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1094. Min Act: -0.0001

Data Index: 526277 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1631. Min Act: -0.0001

Data Index: 609436 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1521336 (Python Code)

Max Activating Token Index: 862

Text #12

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1629. Min Act: -0.0001

Data Index: 861580 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1375. Min Act: -0.0002

Data Index: 904140 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1405. Min Act: -0.0001

Data Index: 171150 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1501. Min Act: -0.0001

Data Index: 136636 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1391421 (Python Code)

Max Activating Token Index: 587

Text #17

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1377. Min Act: -0.0001

Data Index: 851736 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1566. Min Act: -0.0001

Data Index: 10805 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1435632 (Python Code)

Max Activating Token Index: 5