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

Dataset: The Pile

Neuron 3739 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: 1.3376. Min Range: -1.3376

Max Act: 1.2421. Min Act: -0.0000

Data Index: 479888 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.3376. Min Act: -0.0000

Data Index: 1389295 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1827335 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1202. Min Act: -0.0000

Data Index: 352040 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0010. Min Act: -0.0000

Data Index: 424458 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1978367 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0161. Min Act: -0.0000

Data Index: 80811 (The Pile)

Max Activating Token Index: 672

Text #7

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1360370 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1026773 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1200182 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1894597 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.9484. Min Act: -0.0000

Data Index: 642444 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.8772. Min Act: -0.0000

Data Index: 817539 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.9073. Min Act: -0.0000

Data Index: 22297 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1353535 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.9077. Min Act: -0.0000

Data Index: 111100 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1990196 (The Pile)

Max Activating Token Index: 492

Text #17

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1808625 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1202515 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 1.3376. Min Range: -1.3376

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1483796 (The Pile)

Max Activating Token Index: 236