Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 192 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.8756. Min Act: -0.0001

Data Index: 510883 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.8732. Min Act: -0.0001

Data Index: 1169583 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.7588. Min Act: -0.0001

Data Index: 267157 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.7603. Min Act: -0.0001

Data Index: 28412 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6763. Min Act: -0.0001

Data Index: 897163 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.7172. Min Act: -0.0001

Data Index: 1025142 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6709. Min Act: -0.0001

Data Index: 506644 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6288. Min Act: -0.0001

Data Index: 120739 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6933. Min Act: -0.0001

Data Index: 83330 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6716. Min Act: -0.0001

Data Index: 1248737 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6377. Min Act: -0.0001

Data Index: 450392 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6326. Min Act: -0.0001

Data Index: 1077187 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6283. Min Act: -0.0001

Data Index: 160698 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6493. Min Act: -0.0001

Data Index: 529452 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6340. Min Act: -0.0001

Data Index: 520969 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6300. Min Act: -0.0001

Data Index: 840518 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6088. Min Act: -0.0001

Data Index: 728527 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6333. Min Act: -0.0001

Data Index: 507632 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.5825. Min Act: -0.0001

Data Index: 1211980 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.8756. Min Range: -0.8756

Max Act: 0.6207. Min Act: -0.0001

Data Index: 825617 (C4 (Web Text))

Max Activating Token Index: 890