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

Dataset: The Pile

Neuron 1106 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: 0.9310. Min Range: -0.9310

Max Act: 0.9310. Min Act: -0.0000

Data Index: 646151 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8236. Min Act: -0.0000

Data Index: 846997 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1985579 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7683. Min Act: -0.0000

Data Index: 995841 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1259993 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1133288 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7738. Min Act: -0.0000

Data Index: 616717 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7518. Min Act: -0.0000

Data Index: 910339 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6955. Min Act: -0.0000

Data Index: 295480 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6940. Min Act: -0.0000

Data Index: 773827 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1184897 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7281. Min Act: -0.0000

Data Index: 750871 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7145. Min Act: -0.0000

Data Index: 724122 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6755. Min Act: -0.0000

Data Index: 137793 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7111. Min Act: -0.0000

Data Index: 831294 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1219638 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6800. Min Act: -0.0000

Data Index: 532853 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6130. Min Act: -0.0000

Data Index: 617173 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6138. Min Act: -0.0000

Data Index: 467837 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1425249 (The Pile)

Max Activating Token Index: 669