Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1100 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0001

Data Index: 53475 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0620. Min Act: -0.0001

Data Index: 29939 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0660. Min Act: -0.0001

Data Index: 348800 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1444589 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0599. Min Act: -0.0001

Data Index: 800667 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0594. Min Act: -0.0001

Data Index: 278537 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1018247 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0556. Min Act: -0.0001

Data Index: 956802 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0562. Min Act: -0.0001

Data Index: 808180 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0549. Min Act: -0.0001

Data Index: 901922 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0527. Min Act: -0.0001

Data Index: 992699 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0603. Min Act: -0.0001

Data Index: 105015 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0564. Min Act: -0.0001

Data Index: 212952 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0546. Min Act: -0.0001

Data Index: 682390 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1244049 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0528. Min Act: -0.0001

Data Index: 841778 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0523. Min Act: -0.0001

Data Index: 446836 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1104811 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0542. Min Act: -0.0001

Data Index: 1045709 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0501. Min Act: -0.0001

Data Index: 468535 (C4 (Web Text))

Max Activating Token Index: 374