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

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

Neuron 3730 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: 0.0801. Min Range: -0.0801

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1283206 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0782. Min Act: -0.0000

Data Index: 176302 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1184785 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0693. Min Act: -0.0000

Data Index: 161863 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1220028 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0671. Min Act: -0.0000

Data Index: 320908 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0600. Min Act: -0.0000

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1155110 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0628. Min Act: -0.0000

Data Index: 2558 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0597. Min Act: -0.0000

Data Index: 258399 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0573. Min Act: -0.0000

Data Index: 925022 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0550. Min Act: -0.0000

Data Index: 610194 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0607. Min Act: -0.0000

Data Index: 221368 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0533. Min Act: -0.0001

Data Index: 754921 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0553. Min Act: -0.0000

Data Index: 351293 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0553. Min Act: -0.0000

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0532. Min Act: -0.0000

Data Index: 1208632 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0546. Min Act: -0.0000

Data Index: 726900 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0564. Min Act: -0.0000

Data Index: 845799 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1194138 (C4 (Web Text))

Max Activating Token Index: 931