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

Dataset: The Pile

Neuron 5038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.6801. Min Act: -0.0000

Data Index: 839035 (The Pile)

Max Activating Token Index: 205

Text #1

Max Range: 3.0488. Min Range: -3.0488

Max Act: 3.0488. Min Act: -0.0000

Data Index: 775127 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.5202. Min Act: -0.0000

Data Index: 742556 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.0624. Min Act: -0.0000

Data Index: 975986 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.0138. Min Act: -0.0000

Data Index: 1383284 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.3292. Min Act: -0.0000

Data Index: 1380450 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.8652. Min Act: -0.0000

Data Index: 1813806 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.2430. Min Act: -0.0000

Data Index: 1267762 (The Pile)

Max Activating Token Index: 542

Text #8

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.1785. Min Act: -0.0000

Data Index: 1243880 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.9700. Min Act: -0.0000

Data Index: 1455852 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.1100. Min Act: -0.0000

Data Index: 1969491 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.9773. Min Act: -0.0000

Data Index: 1474512 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.8563. Min Act: -0.0000

Data Index: 1412592 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.1835. Min Act: -0.0000

Data Index: 23289 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1136311 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.9365. Min Act: -0.0000

Data Index: 418881 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.6357. Min Act: -0.0000

Data Index: 1951136 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 3.0488. Min Range: -3.0488

Max Act: 2.1584. Min Act: -0.0000

Data Index: 1547882 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.8727. Min Act: -0.0000

Data Index: 184449 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 3.0488. Min Range: -3.0488

Max Act: 1.6882. Min Act: -0.0000

Data Index: 391358 (The Pile)

Max Activating Token Index: 685