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

Dataset: The Pile

Neuron 3404 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: 1.6500. Min Range: -1.6500

Max Act: 1.5919. Min Act: -0.0000

Data Index: 1330282 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1994144 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.6500. Min Act: -0.0000

Data Index: 892266 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.5113. Min Act: -0.0000

Data Index: 637737 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.4237. Min Act: -0.0000

Data Index: 614563 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.4591. Min Act: -0.0000

Data Index: 1125272 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.4265. Min Act: -0.0000

Data Index: 868341 (The Pile)

Max Activating Token Index: 852

Text #7

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1705671 (The Pile)

Max Activating Token Index: 799

Text #8

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.4420. Min Act: -0.0000

Data Index: 357843 (The Pile)

Max Activating Token Index: 915

Text #9

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.3534. Min Act: -0.0000

Data Index: 209552 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1889364 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.3364. Min Act: -0.0000

Data Index: 1700935 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.3251. Min Act: -0.0000

Data Index: 1240810 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.2472. Min Act: -0.0000

Data Index: 1170235 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.3072. Min Act: -0.0000

Data Index: 586264 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1453804 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.3041. Min Act: -0.0000

Data Index: 18353 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1886802 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1801606 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 1.6500. Min Range: -1.6500

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1965541 (The Pile)

Max Activating Token Index: 953