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

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

Neuron 4427 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1615777 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1596325 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1594075 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1466851 (Python Code)

Max Activating Token Index: 537

Text #4

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1628786 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1589566 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1586623 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1382059 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1567574 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1180812 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1494816 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1538942 (Python Code)

Max Activating Token Index: 45

Text #12

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1622410 (Python Code)

Max Activating Token Index: 608

Text #13

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1445765 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1475486 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1539655 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1388712 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1482245 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1363796 (Python Code)

Max Activating Token Index: 278

Text #19

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1599460 (Python Code)

Max Activating Token Index: 378