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

Dataset: The Pile

Neuron 3393 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1607336 (The Pile)

Max Activating Token Index: 147

Text #1

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.9032. Min Act: -0.0000

Data Index: 322276 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.8908. Min Act: -0.0000

Data Index: 307160 (The Pile)

Max Activating Token Index: 753

Text #3

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1007894 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.7576. Min Act: -0.0000

Data Index: 940554 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.7869. Min Act: -0.0000

Data Index: 504667 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1471477 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.6177. Min Act: -0.0000

Data Index: 158653 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1387028 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.6102. Min Act: -0.0000

Data Index: 809695 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5545. Min Act: -0.0000

Data Index: 42044 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1635299 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1610506 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5621. Min Act: -0.0000

Data Index: 48869 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1184135 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5851. Min Act: -0.0000

Data Index: 137287 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1481911 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1445750 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5514. Min Act: -0.0000

Data Index: 595244 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 0.9032. Min Range: -0.9032

Max Act: 0.5722. Min Act: -0.0000

Data Index: 410191 (The Pile)

Max Activating Token Index: 436