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

Dataset: The Pile

Neuron 4161 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: 5.5165. Min Range: -5.5165

Max Act: 5.5165. Min Act: -0.0000

Data Index: 279189 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 5.5165. Min Range: -5.5165

Max Act: 5.3655. Min Act: -0.0000

Data Index: 1103473 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 5.5165. Min Range: -5.5165

Max Act: 5.3434. Min Act: -0.0000

Data Index: 1949575 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.9125. Min Act: -0.0000

Data Index: 916920 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 5.5165. Min Range: -5.5165

Max Act: 5.0867. Min Act: -0.0000

Data Index: 978210 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.6119. Min Act: -0.0000

Data Index: 112258 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.9406. Min Act: -0.0000

Data Index: 187082 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.9335. Min Act: -0.0000

Data Index: 576090 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.7266. Min Act: -0.0000

Data Index: 840896 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.7223. Min Act: -0.0000

Data Index: 153751 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.7702. Min Act: -0.0000

Data Index: 1140350 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.3482. Min Act: -0.0000

Data Index: 1432575 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.4889. Min Act: -0.0000

Data Index: 950427 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.4595. Min Act: -0.0000

Data Index: 390768 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.6246. Min Act: -0.0000

Data Index: 771739 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.5688. Min Act: -0.0000

Data Index: 1065532 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.4103. Min Act: -0.0000

Data Index: 1251417 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.5596. Min Act: -0.0000

Data Index: 988721 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.5544. Min Act: -0.0000

Data Index: 1108952 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 5.5165. Min Range: -5.5165

Max Act: 4.3232. Min Act: -0.0000

Data Index: 1005827 (The Pile)

Max Activating Token Index: 598