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

Dataset: The Pile

Neuron 3290 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: 3.9944. Min Range: -3.9944

Max Act: 3.7471. Min Act: -0.0000

Data Index: 346827 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.9944. Min Act: -0.0000

Data Index: 1646354 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.5170. Min Act: -0.0000

Data Index: 759 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.8406. Min Act: -0.0000

Data Index: 930267 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.6026. Min Act: -0.0000

Data Index: 99358 (The Pile)

Max Activating Token Index: 256

Text #5

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.2376. Min Act: -0.0000

Data Index: 48971 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.5022. Min Act: -0.0000

Data Index: 881637 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.3320. Min Act: -0.0000

Data Index: 33119 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.4682. Min Act: -0.0000

Data Index: 867381 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.4086. Min Act: -0.0000

Data Index: 931716 (The Pile)

Max Activating Token Index: 569

Text #10

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.4000. Min Act: -0.0000

Data Index: 1603201 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.2084. Min Act: -0.0000

Data Index: 1220363 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.3344. Min Act: -0.0000

Data Index: 211662 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.3447. Min Act: -0.0000

Data Index: 993703 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.2703. Min Act: -0.0000

Data Index: 917515 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.1062. Min Act: -0.0000

Data Index: 443802 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.1234. Min Act: -0.0000

Data Index: 781788 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 3.9944. Min Range: -3.9944

Max Act: 2.9860. Min Act: -0.0000

Data Index: 220087 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.2184. Min Act: -0.0000

Data Index: 275444 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.2063. Min Act: -0.0000

Data Index: 311001 (The Pile)

Max Activating Token Index: 72