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

Dataset: The Pile

Neuron 1808 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: 0.3840. Min Range: -0.3840

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1936626 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3595. Min Act: -0.0000

Data Index: 404253 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1800432 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2844. Min Act: -0.0000

Data Index: 885517 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1719849 (The Pile)

Max Activating Token Index: 992

Text #5

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1214374 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1517952 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1558645 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2603. Min Act: -0.0000

Data Index: 222422 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1543319 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2293. Min Act: -0.0000

Data Index: 823298 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2194. Min Act: -0.0000

Data Index: 818795 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2493. Min Act: -0.0000

Data Index: 555900 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1667498 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1397282 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2461. Min Act: -0.0000

Data Index: 560489 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2319. Min Act: -0.0000

Data Index: 259975 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1211961 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.2354. Min Act: -0.0000

Data Index: 776766 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.3840. Min Range: -0.3840

Max Act: 0.1902. Min Act: -0.0000

Data Index: 437197 (The Pile)

Max Activating Token Index: 912