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

Dataset: The Pile

Neuron 512 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7927. Min Act: -0.0000

Data Index: 327682 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7827. Min Act: -0.0000

Data Index: 436245 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1481514 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7617. Min Act: -0.0000

Data Index: 425704 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1949587 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1090007 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7254. Min Act: -0.0000

Data Index: 626423 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1755343 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7228. Min Act: -0.0000

Data Index: 805012 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7382. Min Act: -0.0000

Data Index: 999150 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.7151. Min Act: -0.0000

Data Index: 62650 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6684. Min Act: -0.0000

Data Index: 116355 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1395 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6641. Min Act: -0.0000

Data Index: 585421 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5924. Min Act: -0.0000

Data Index: 123844 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1485783 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1470877 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6452. Min Act: -0.0000

Data Index: 589293 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1081029 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1980289 (The Pile)

Max Activating Token Index: 666