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

Dataset: The Pile

Neuron 3559 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: 1.2498. Min Range: -1.2498

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1644617 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1715609 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.2151. Min Act: -0.0000

Data Index: 935461 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1366105 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.1036. Min Act: -0.0000

Data Index: 775117 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0864. Min Act: -0.0000

Data Index: 991583 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1208723 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0703. Min Act: -0.0000

Data Index: 360009 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0223. Min Act: -0.0000

Data Index: 821828 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1382534 (The Pile)

Max Activating Token Index: 694

Text #10

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1762704 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1581784 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9909. Min Act: -0.0000

Data Index: 109224 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9421. Min Act: -0.0000

Data Index: 237850 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0351. Min Act: -0.0000

Data Index: 429030 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1792414 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1540075 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1537311 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9217. Min Act: -0.0000

Data Index: 465773 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1113276 (The Pile)

Max Activating Token Index: 361