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

Dataset: The Pile

Neuron 3669 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5720. Min Range: -4.5720

Max Act: 4.5720. Min Act: -0.0000

Data Index: 442074 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.4370. Min Act: 0.0000

Data Index: 1856525 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.3796. Min Act: -0.0000

Data Index: 636343 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.4243. Min Act: -0.0000

Data Index: 27986 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.7414. Min Act: -0.0000

Data Index: 1381985 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.6895. Min Act: -0.0000

Data Index: 1068436 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.4228. Min Act: -0.0000

Data Index: 1529574 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.4331. Min Act: -0.0000

Data Index: 1654004 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.2392. Min Act: -0.0000

Data Index: 1272439 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.6659. Min Act: -0.0000

Data Index: 666257 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.3698. Min Act: -0.0000

Data Index: 482241 (The Pile)

Max Activating Token Index: 917

Text #11

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.3449. Min Act: -0.0000

Data Index: 1816309 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.0289. Min Act: 0.0000

Data Index: 1321198 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.1009. Min Act: -0.0000

Data Index: 470121 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.0622. Min Act: -0.0000

Data Index: 1903062 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.1459. Min Act: -0.0000

Data Index: 1545084 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.0196. Min Act: -0.0000

Data Index: 612394 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 4.5720. Min Range: -4.5720

Max Act: 2.9858. Min Act: -0.0000

Data Index: 410788 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.1423. Min Act: -0.0000

Data Index: 1719233 (The Pile)

Max Activating Token Index: 918

Text #19

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.0973. Min Act: -0.0000

Data Index: 827277 (The Pile)

Max Activating Token Index: 612