Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 81 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.7583. Min Act: -0.0000

Data Index: 1170294 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.4035. Min Act: -0.0000

Data Index: 1712656 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1168302 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.3564. Min Act: -0.0000

Data Index: 528501 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.3949. Min Act: -0.0000

Data Index: 767361 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.2351. Min Act: -0.0000

Data Index: 468404 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.1246. Min Act: -0.0000

Data Index: 431669 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.2950. Min Act: -0.0000

Data Index: 1362411 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.2522. Min Act: -0.0000

Data Index: 1467376 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.1818. Min Act: -0.0000

Data Index: 297127 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.2188. Min Act: -0.0000

Data Index: 36609 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1945185 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1779290 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1078599 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.0916. Min Act: -0.0000

Data Index: 353118 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.1250. Min Act: -0.0000

Data Index: 10344 (The Pile)

Max Activating Token Index: 667

Text #16

Max Range: 1.7583. Min Range: -1.7583

Max Act: 0.9894. Min Act: -0.0000

Data Index: 650489 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1711444 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 1.7583. Min Range: -1.7583

Max Act: 1.0237. Min Act: -0.0000

Data Index: 157064 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 1.7583. Min Range: -1.7583

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1451533 (The Pile)

Max Activating Token Index: 1002