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

Dataset: The Pile

Neuron 1328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.7184. Min Act: -0.0000

Data Index: 231350 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6508. Min Act: -0.0000

Data Index: 272466 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5907. Min Act: -0.0000

Data Index: 913351 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5960. Min Act: -0.0000

Data Index: 960735 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1494726 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6696. Min Act: -0.0000

Data Index: 530350 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5802. Min Act: -0.0000

Data Index: 618988 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1671074 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5744. Min Act: -0.0000

Data Index: 313753 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1709504 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4911. Min Act: -0.0000

Data Index: 61728 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4933. Min Act: -0.0000

Data Index: 13582 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1253608 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1358195 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1746640 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1293962 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4898. Min Act: -0.0000

Data Index: 68373 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4720. Min Act: -0.0000

Data Index: 889068 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1061587 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4648. Min Act: -0.0000

Data Index: 363112 (The Pile)

Max Activating Token Index: 461