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

Dataset: The Pile

Neuron 3449 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: 0.4994. Min Range: -0.4994

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1334840 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1927337 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4842. Min Act: -0.0000

Data Index: 108847 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4173. Min Act: -0.0000

Data Index: 171740 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4082. Min Act: -0.0000

Data Index: 64881 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3735. Min Act: -0.0000

Data Index: 568262 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3642. Min Act: -0.0000

Data Index: 142003 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1207569 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3477. Min Act: -0.0000

Data Index: 364578 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1075871 (The Pile)

Max Activating Token Index: 455

Text #10

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3628. Min Act: -0.0000

Data Index: 493167 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3521. Min Act: -0.0000

Data Index: 348232 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1397341 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1394343 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3412. Min Act: -0.0000

Data Index: 628711 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3340. Min Act: -0.0000

Data Index: 545895 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1881700 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1999729 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1006459 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3107. Min Act: -0.0000

Data Index: 290387 (The Pile)

Max Activating Token Index: 185