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

Dataset: The Pile

Neuron 827 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: 0.7275. Min Range: -0.7275

Max Act: 0.7275. Min Act: -0.0000

Data Index: 364849 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6662. Min Act: -0.0000

Data Index: 880521 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1601578 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6763. Min Act: -0.0000

Data Index: 290537 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5881. Min Act: -0.0000

Data Index: 646091 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6296. Min Act: -0.0000

Data Index: 278255 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6717. Min Act: -0.0000

Data Index: 396454 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6094. Min Act: -0.0000

Data Index: 976332 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1399106 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1494425 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5739. Min Act: -0.0000

Data Index: 713015 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5851. Min Act: -0.0000

Data Index: 895719 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5218. Min Act: -0.0000

Data Index: 296297 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5082. Min Act: -0.0000

Data Index: 363801 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1653681 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5001. Min Act: -0.0000

Data Index: 760691 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1019347 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5415. Min Act: -0.0000

Data Index: 894883 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5189. Min Act: -0.0000

Data Index: 623485 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5121. Min Act: -0.0000

Data Index: 527644 (The Pile)

Max Activating Token Index: 456