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

Dataset: The Pile

Neuron 1638 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: 1.4022. Min Range: -1.4022

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1133386 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1948112 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2761. Min Act: -0.0000

Data Index: 213727 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1327968 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1672. Min Act: -0.0000

Data Index: 936046 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1405979 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1011982 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2332. Min Act: -0.0000

Data Index: 168290 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1518. Min Act: -0.0000

Data Index: 131437 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2395. Min Act: -0.0000

Data Index: 368654 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.3037. Min Act: -0.0000

Data Index: 655585 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1160196 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1028309 (The Pile)

Max Activating Token Index: 335

Text #13

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0676. Min Act: -0.0000

Data Index: 1498254 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1159174 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1715. Min Act: -0.0000

Data Index: 676696 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1306320 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1300159 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1888917 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1476. Min Act: -0.0000

Data Index: 1671743 (The Pile)

Max Activating Token Index: 156