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

Dataset: The Pile

Neuron 1651 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.3144. Min Act: -0.0000

Data Index: 331596 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.3358. Min Act: -0.0000

Data Index: 1699614 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.3290. Min Act: -0.0000

Data Index: 390108 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.3243. Min Act: -0.0000

Data Index: 394963 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.4662. Min Act: -0.0000

Data Index: 1152170 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.3077. Min Act: -0.0000

Data Index: 291520 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1697. Min Act: -0.0000

Data Index: 452087 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1802. Min Act: -0.0000

Data Index: 171307 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1641. Min Act: -0.0000

Data Index: 1169292 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1683. Min Act: -0.0000

Data Index: 490749 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.3096. Min Act: -0.0000

Data Index: 944065 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1540. Min Act: -0.0000

Data Index: 1356872 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1675. Min Act: -0.0000

Data Index: 1393357 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1501. Min Act: -0.0000

Data Index: 944816 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.1307. Min Act: -0.0000

Data Index: 584295 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.0326. Min Act: -0.0000

Data Index: 1262883 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.0190. Min Act: -0.0000

Data Index: 632716 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 3.4662. Min Range: -3.4662

Max Act: 2.8681. Min Act: -0.0000

Data Index: 1311024 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 3.4662. Min Range: -3.4662

Max Act: 3.0025. Min Act: -0.0000

Data Index: 1230278 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 3.4662. Min Range: -3.4662

Max Act: 2.9965. Min Act: -0.0000

Data Index: 1775624 (The Pile)

Max Activating Token Index: 416