Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 240 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 7.6679. Min Range: -7.6679

Max Act: 7.6679. Min Act: -0.0000

Data Index: 1461403 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 7.6679. Min Range: -7.6679

Max Act: 7.2565. Min Act: -0.0000

Data Index: 1603007 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.8994. Min Act: -0.0000

Data Index: 1528624 (Python Code)

Max Activating Token Index: 772

Text #3

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.6784. Min Act: -0.0000

Data Index: 1515830 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 7.6679. Min Range: -7.6679

Max Act: 7.0109. Min Act: -0.0000

Data Index: 1495522 (Python Code)

Max Activating Token Index: 718

Text #5

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.2678. Min Act: -0.0001

Data Index: 1377903 (Python Code)

Max Activating Token Index: 689

Text #6

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.7097. Min Act: -0.0000

Data Index: 1508171 (Python Code)

Max Activating Token Index: 723

Text #7

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.8590. Min Act: -0.0000

Data Index: 1488010 (Python Code)

Max Activating Token Index: 684

Text #8

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.6859. Min Act: -0.0001

Data Index: 1402348 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.6208. Min Act: -0.0000

Data Index: 1500909 (Python Code)

Max Activating Token Index: 375

Text #10

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.1622. Min Act: -0.0001

Data Index: 1562639 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.3277. Min Act: -0.0000

Data Index: 1433551 (Python Code)

Max Activating Token Index: 335

Text #12

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.1091. Min Act: -0.0000

Data Index: 1413082 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.4238. Min Act: -0.0001

Data Index: 1532945 (Python Code)

Max Activating Token Index: 569

Text #14

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.2140. Min Act: -0.0000

Data Index: 1393746 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.2435. Min Act: -0.0000

Data Index: 1451032 (Python Code)

Max Activating Token Index: 627

Text #16

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.0315. Min Act: -0.0000

Data Index: 1510437 (Python Code)

Max Activating Token Index: 607

Text #17

Max Range: 7.6679. Min Range: -7.6679

Max Act: 5.8535. Min Act: -0.0000

Data Index: 1626672 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.3735. Min Act: -0.0000

Data Index: 1620692 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 7.6679. Min Range: -7.6679

Max Act: 6.1852. Min Act: -0.0000

Data Index: 1643832 (Python Code)

Max Activating Token Index: 102