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

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

Neuron 3994 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.4673. Min Act: -0.0000

Data Index: 374579 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.4212. Min Act: -0.0000

Data Index: 28397 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1577697 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.3071. Min Act: -0.0000

Data Index: 238333 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1501240 (Python Code)

Max Activating Token Index: 914

Text #5

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1437570 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2483. Min Act: -0.0000

Data Index: 407838 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1537. Min Act: -0.0000

Data Index: 655032 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1612. Min Act: -0.0000

Data Index: 260731 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2268. Min Act: -0.0000

Data Index: 954642 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 1.4673. Min Range: -1.4673

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1522395 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1990. Min Act: -0.0000

Data Index: 201845 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 1.4673. Min Range: -1.4673

Max Act: 0.9525. Min Act: -0.0000

Data Index: 837828 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0497. Min Act: -0.0000

Data Index: 267727 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0440. Min Act: -0.0000

Data Index: 24137 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.2011. Min Act: -0.0000

Data Index: 470196 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0933. Min Act: -0.0000

Data Index: 531039 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1568525 (Python Code)

Max Activating Token Index: 615

Text #18

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1166999 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.4673. Min Range: -1.4673

Max Act: 1.0578. Min Act: -0.0000

Data Index: 626409 (C4 (Web Text))

Max Activating Token Index: 955