Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1887 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0722. Min Range: -1.0722

Max Act: 1.0722. Min Act: -0.0001

Data Index: 1565013 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9576. Min Act: -0.0001

Data Index: 1435212 (Python Code)

Max Activating Token Index: 182

Text #2

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1599672 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9688. Min Act: -0.0001

Data Index: 1482414 (Python Code)

Max Activating Token Index: 814

Text #4

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9240. Min Act: -0.0001

Data Index: 1363342 (Python Code)

Max Activating Token Index: 923

Text #5

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9046. Min Act: -0.0001

Data Index: 1445877 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9189. Min Act: -0.0001

Data Index: 1360636 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 1.0722. Min Range: -1.0722

Max Act: 1.0403. Min Act: -0.0001

Data Index: 1462285 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9136. Min Act: -0.0001

Data Index: 1533451 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.8812. Min Act: -0.0001

Data Index: 1534873 (Python Code)

Max Activating Token Index: 246

Text #10

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9021. Min Act: -0.0001

Data Index: 1513860 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.8359. Min Act: -0.0001

Data Index: 1649284 (Python Code)

Max Activating Token Index: 160

Text #12

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.8683. Min Act: -0.0001

Data Index: 1551260 (Python Code)

Max Activating Token Index: 442

Text #13

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1638804 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1458013 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1360666 (Python Code)

Max Activating Token Index: 593

Text #16

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.8872. Min Act: -0.0001

Data Index: 1472843 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.9086. Min Act: -0.0001

Data Index: 1552486 (Python Code)

Max Activating Token Index: 943

Text #18

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.8478. Min Act: -0.0001

Data Index: 1596608 (Python Code)

Max Activating Token Index: 337

Text #19

Max Range: 1.0722. Min Range: -1.0722

Max Act: 0.8735. Min Act: -0.0001

Data Index: 1385428 (Python Code)

Max Activating Token Index: 803