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

Dataset: The Pile

Neuron 2483 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: 0.9482. Min Range: -0.9482

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1671934 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1058053 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8791. Min Act: -0.0000

Data Index: 356580 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8979. Min Act: -0.0000

Data Index: 414261 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8652. Min Act: -0.0000

Data Index: 705429 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8865. Min Act: -0.0000

Data Index: 688822 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8679. Min Act: -0.0000

Data Index: 895063 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1519406 (The Pile)

Max Activating Token Index: 777

Text #8

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8751. Min Act: -0.0000

Data Index: 307119 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7838. Min Act: -0.0000

Data Index: 557380 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7927. Min Act: -0.0000

Data Index: 522465 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1361738 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8717. Min Act: -0.0000

Data Index: 250488 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7857. Min Act: -0.0000

Data Index: 378862 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1940875 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7982. Min Act: -0.0000

Data Index: 955939 (The Pile)

Max Activating Token Index: 257

Text #16

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7996. Min Act: -0.0000

Data Index: 789580 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8009. Min Act: -0.0000

Data Index: 787630 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1150195 (The Pile)

Max Activating Token Index: 677

Text #19

Max Range: 0.9482. Min Range: -0.9482

Max Act: 0.8170. Min Act: -0.0000

Data Index: 243977 (The Pile)

Max Activating Token Index: 754