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

Dataset: The Pile

Neuron 410 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: 1.2993. Min Range: -1.2993

Max Act: 1.2993. Min Act: -0.0000

Data Index: 1244146 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1276358 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0901. Min Act: -0.0000

Data Index: 652494 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0152. Min Act: -0.0000

Data Index: 159382 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1474198 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9858. Min Act: -0.0000

Data Index: 584916 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1810408 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1978892 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1303028 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1783459 (The Pile)

Max Activating Token Index: 872

Text #10

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8701. Min Act: 0.0000

Data Index: 58911 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1860110 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1699150 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1954409 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8480. Min Act: -0.0000

Data Index: 183704 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.7803. Min Act: -0.0000

Data Index: 623700 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.7946. Min Act: -0.0000

Data Index: 888276 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8226. Min Act: -0.0000

Data Index: 711540 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.7799. Min Act: -0.0000

Data Index: 138340 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1603301 (The Pile)

Max Activating Token Index: 602