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

Dataset: The Pile

Neuron 4921 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: 1.3310. Min Range: -1.3310

Max Act: 1.3310. Min Act: -0.0000

Data Index: 725876 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0780. Min Act: -0.0000

Data Index: 623286 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1201710 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.1842. Min Act: -0.0000

Data Index: 1824002 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0875. Min Act: -0.0000

Data Index: 124680 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1533701 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0152. Min Act: -0.0000

Data Index: 15402 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9940. Min Act: -0.0000

Data Index: 30753 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1651291 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0073. Min Act: -0.0000

Data Index: 319588 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9705. Min Act: -0.0000

Data Index: 905161 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9582. Min Act: -0.0000

Data Index: 104274 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9828. Min Act: -0.0000

Data Index: 891579 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.8894. Min Act: -0.0000

Data Index: 10551 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1731894 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9721. Min Act: -0.0000

Data Index: 183299 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1605169 (The Pile)

Max Activating Token Index: 405

Text #17

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.8438. Min Act: -0.0000

Data Index: 245608 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1702454 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.8945. Min Act: -0.0000

Data Index: 250692 (The Pile)

Max Activating Token Index: 374