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

Dataset: The Pile

Neuron 3740 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1488172 (The Pile)

Max Activating Token Index: 707

Text #1

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5925. Min Act: -0.0000

Data Index: 899223 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6011. Min Act: 0.0000

Data Index: 1405001 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1048546 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1543033 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5395. Min Act: -0.0000

Data Index: 460666 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5608. Min Act: -0.0000

Data Index: 964557 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4898. Min Act: -0.0000

Data Index: 603522 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4784. Min Act: -0.0000

Data Index: 30681 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5041. Min Act: -0.0000

Data Index: 246526 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1477925 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4638. Min Act: -0.0000

Data Index: 597301 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1818284 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1597546 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4389. Min Act: -0.0000

Data Index: 172025 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1935266 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.3970. Min Act: -0.0000

Data Index: 328140 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4143. Min Act: -0.0000

Data Index: 616640 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.3796. Min Act: 0.0000

Data Index: 316038 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.3875. Min Act: -0.0000

Data Index: 571867 (The Pile)

Max Activating Token Index: 490