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

Dataset: The Pile

Neuron 889 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: 0.6356. Min Range: -0.6356

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1574862 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5994. Min Act: -0.0000

Data Index: 746577 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5073. Min Act: -0.0000

Data Index: 894264 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4790. Min Act: -0.0000

Data Index: 964492 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4687. Min Act: -0.0000

Data Index: 589331 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1821935 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4620. Min Act: -0.0000

Data Index: 665021 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4321. Min Act: -0.0000

Data Index: 646024 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4587. Min Act: -0.0000

Data Index: 300678 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1572559 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4403. Min Act: -0.0000

Data Index: 599932 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4283. Min Act: 0.0001

Data Index: 1629782 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4277. Min Act: -0.0000

Data Index: 790062 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1821457 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1242857 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.3977. Min Act: -0.0000

Data Index: 506481 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4000. Min Act: -0.0000

Data Index: 193476 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1643081 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.3885. Min Act: -0.0000

Data Index: 352323 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1254164 (The Pile)

Max Activating Token Index: 19