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

Dataset: The Pile

Neuron 4934 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: 0.7030. Min Range: -0.7030

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1842890 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6702. Min Act: -0.0000

Data Index: 242696 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6691. Min Act: -0.0000

Data Index: 513852 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1348752 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5958. Min Act: -0.0000

Data Index: 758150 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6138. Min Act: -0.0000

Data Index: 411529 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6566. Min Act: -0.0000

Data Index: 954574 (The Pile)

Max Activating Token Index: 319

Text #7

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1292501 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5817. Min Act: -0.0000

Data Index: 390657 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1802694 (The Pile)

Max Activating Token Index: 488

Text #10

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6093. Min Act: -0.0000

Data Index: 377578 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1378143 (The Pile)

Max Activating Token Index: 400

Text #12

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1617672 (The Pile)

Max Activating Token Index: 240

Text #13

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1533543 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1004660 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6217. Min Act: -0.0000

Data Index: 226247 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5359. Min Act: 0.0000

Data Index: 1269974 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1245093 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5662. Min Act: -0.0000

Data Index: 112944 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1870860 (The Pile)

Max Activating Token Index: 516