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

Dataset: The Pile

Neuron 3536 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1452184 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.3272. Min Act: -0.0000

Data Index: 67356 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1125751 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0653. Min Act: -0.0000

Data Index: 778660 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1200936 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1074705 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1780727 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0468. Min Act: -0.0000

Data Index: 472944 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1092631 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9386. Min Act: -0.0000

Data Index: 944495 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1649392 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.8904. Min Act: -0.0000

Data Index: 555027 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.8849. Min Act: -0.0000

Data Index: 534141 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.7711. Min Act: -0.0000

Data Index: 887911 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.8993. Min Act: -0.0000

Data Index: 923384 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1174879 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.7827. Min Act: -0.0000

Data Index: 277044 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.8571. Min Act: -0.0000

Data Index: 680258 (The Pile)

Max Activating Token Index: 239

Text #18

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.8157. Min Act: -0.0000

Data Index: 39864 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.8399. Min Act: 0.0000

Data Index: 70226 (The Pile)

Max Activating Token Index: 195