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

Dataset: The Pile

Neuron 611 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0765. Min Range: -1.0765

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1450807 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 1.0765. Min Range: -1.0765

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1937932 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.0765. Min Range: -1.0765

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1354861 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9898. Min Act: -0.0000

Data Index: 995243 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1038782 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1022623 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1381029 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1741470 (The Pile)

Max Activating Token Index: 209

Text #8

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9535. Min Act: -0.0000

Data Index: 476538 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9371. Min Act: -0.0000

Data Index: 576840 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9322. Min Act: -0.0000

Data Index: 226266 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1508361 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1592599 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1469643 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8658. Min Act: -0.0000

Data Index: 658181 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1275098 (The Pile)

Max Activating Token Index: 303

Text #16

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9139. Min Act: -0.0000

Data Index: 309313 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1143920 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8526. Min Act: -0.0000

Data Index: 696848 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.9073. Min Act: -0.0000

Data Index: 82307 (The Pile)

Max Activating Token Index: 438