Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5376 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6813. Min Act: -0.0000

Data Index: 1060896 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.8373. Min Act: -0.0000

Data Index: 388425 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6523. Min Act: -0.0000

Data Index: 167313 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.2920. Min Act: -0.0000

Data Index: 603638 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.3396. Min Act: -0.0000

Data Index: 1136266 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.2708. Min Act: -0.0000

Data Index: 45122 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.2648. Min Act: -0.0000

Data Index: 233702 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.3477. Min Act: -0.0000

Data Index: 879236 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.1751. Min Act: -0.0000

Data Index: 862737 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.8424. Min Act: -0.0000

Data Index: 7041 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.0851. Min Act: -0.0000

Data Index: 907891 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.0133. Min Act: -0.0000

Data Index: 1132778 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.9951. Min Act: -0.0000

Data Index: 1259025 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.8230. Min Act: -0.0000

Data Index: 269133 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.8210. Min Act: -0.0000

Data Index: 960324 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.9471. Min Act: -0.0000

Data Index: 357628 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.8996. Min Act: -0.0000

Data Index: 397945 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.8599. Min Act: -0.0000

Data Index: 229230 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.6570. Min Act: -0.0000

Data Index: 56661 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 3.8373. Min Range: -3.8373

Max Act: 2.9104. Min Act: -0.0000

Data Index: 309819 (C4 (Web Text))

Max Activating Token Index: 331