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

Dataset: The Pile

Neuron 1465 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: 3.0205. Min Range: -3.0205

Max Act: 2.9636. Min Act: -0.0000

Data Index: 1362294 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.9856. Min Act: -0.0000

Data Index: 1808402 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.7850. Min Act: -0.0000

Data Index: 1023021 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 3.0205. Min Range: -3.0205

Max Act: 3.0205. Min Act: -0.0000

Data Index: 1767289 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.3964. Min Act: -0.0000

Data Index: 296412 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.0928. Min Act: -0.0000

Data Index: 81994 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.5262. Min Act: -0.0000

Data Index: 802031 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.5568. Min Act: -0.0000

Data Index: 1772115 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.2974. Min Act: -0.0000

Data Index: 646029 (The Pile)

Max Activating Token Index: 832

Text #9

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.1571. Min Act: -0.0000

Data Index: 787087 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.3200. Min Act: -0.0000

Data Index: 1703884 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.2489. Min Act: -0.0000

Data Index: 1286405 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.4170. Min Act: -0.0000

Data Index: 1211154 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.1121. Min Act: -0.0000

Data Index: 1448103 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.2420. Min Act: -0.0000

Data Index: 769609 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.2401. Min Act: -0.0000

Data Index: 1790162 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.0764. Min Act: -0.0000

Data Index: 925673 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.1946. Min Act: -0.0000

Data Index: 471692 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 3.0205. Min Range: -3.0205

Max Act: 2.1738. Min Act: -0.0000

Data Index: 7342 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 3.0205. Min Range: -3.0205

Max Act: 1.9271. Min Act: -0.0000

Data Index: 1982644 (The Pile)

Max Activating Token Index: 739