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

Dataset: The Pile

Neuron 2871 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: 1.3054. Min Range: -1.3054

Max Act: 1.3054. Min Act: -0.0000

Data Index: 814667 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1503555 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.1917. Min Act: -0.0000

Data Index: 496032 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1798608 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.1476. Min Act: -0.0000

Data Index: 21605 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1870627 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.0209. Min Act: -0.0000

Data Index: 534086 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.0408. Min Act: -0.0000

Data Index: 798485 (The Pile)

Max Activating Token Index: 317

Text #8

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.0540. Min Act: -0.0000

Data Index: 302101 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 1.3054. Min Range: -1.3054

Max Act: 0.9513. Min Act: -0.0000

Data Index: 529792 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1250501 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 1.3054. Min Range: -1.3054

Max Act: 0.9318. Min Act: -0.0000

Data Index: 654818 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 1.3054. Min Range: -1.3054

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1940176 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 1.3054. Min Range: -1.3054

Max Act: 0.9671. Min Act: -0.0000

Data Index: 117468 (The Pile)

Max Activating Token Index: 355

Text #14

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.0226. Min Act: -0.0000

Data Index: 652969 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 1.3054. Min Range: -1.3054

Max Act: 0.9532. Min Act: -0.0000

Data Index: 807313 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 1.3054. Min Range: -1.3054

Max Act: 1.0336. Min Act: -0.0000

Data Index: 609112 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 1.3054. Min Range: -1.3054

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1667826 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 1.3054. Min Range: -1.3054

Max Act: 0.8985. Min Act: -0.0000

Data Index: 111940 (The Pile)

Max Activating Token Index: 991

Text #19

Max Range: 1.3054. Min Range: -1.3054

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1193762 (The Pile)

Max Activating Token Index: 994