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

Dataset: The Pile

Neuron 3388 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1999796 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1180954 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5994. Min Act: -0.0000

Data Index: 69368 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5901. Min Act: 0.0000

Data Index: 1426622 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1952859 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.6038. Min Act: -0.0000

Data Index: 814249 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5878. Min Act: 0.0000

Data Index: 1761219 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1191260 (The Pile)

Max Activating Token Index: 843

Text #8

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1901528 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1273376 (The Pile)

Max Activating Token Index: 800

Text #10

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5266. Min Act: -0.0000

Data Index: 551757 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5227. Min Act: -0.0000

Data Index: 913271 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1595443 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4964. Min Act: -0.0000

Data Index: 344412 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5341. Min Act: -0.0000

Data Index: 140642 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1800139 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4644. Min Act: -0.0000

Data Index: 311504 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.5114. Min Act: -0.0000

Data Index: 296906 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4925. Min Act: -0.0000

Data Index: 323875 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.6969. Min Range: -0.6969

Max Act: 0.4684. Min Act: -0.0000

Data Index: 73126 (The Pile)

Max Activating Token Index: 484