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

Dataset: The Pile

Neuron 711 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7765. Min Act: -0.0000

Data Index: 854614 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1637066 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1149595 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1015664 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1371388 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1857893 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1637166 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5668. Min Act: -0.0000

Data Index: 104070 (The Pile)

Max Activating Token Index: 754

Text #8

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6736. Min Act: -0.0000

Data Index: 773926 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1789607 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1597638 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1980757 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1154811 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1297371 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5070. Min Act: -0.0000

Data Index: 688603 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5902. Min Act: -0.0000

Data Index: 70226 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1672287 (The Pile)

Max Activating Token Index: 733

Text #17

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1589110 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1778139 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 0.7765. Min Range: -0.7765

Max Act: 0.5948. Min Act: -0.0000

Data Index: 725068 (The Pile)

Max Activating Token Index: 26