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

Dataset: The Pile

Neuron 3064 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.7275. Min Act: -0.0000

Data Index: 423233 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4909. Min Act: -0.0000

Data Index: 696230 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1017182 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5624. Min Act: -0.0000

Data Index: 897963 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5023. Min Act: -0.0000

Data Index: 859608 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1043420 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5473. Min Act: -0.0000

Data Index: 579864 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1820447 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1445127 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4841. Min Act: 0.0000

Data Index: 1733351 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1007992 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1367910 (The Pile)

Max Activating Token Index: 608

Text #12

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1928884 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1133276 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1099246 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4899. Min Act: -0.0000

Data Index: 324296 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1887831 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1827551 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1803942 (The Pile)

Max Activating Token Index: 50

Text #19

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1784329 (The Pile)

Max Activating Token Index: 302