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

Dataset: The Pile

Neuron 2649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1506597 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1460506 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1886118 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9691. Min Act: -0.0000

Data Index: 554517 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1285660 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1388854 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1685692 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.8196. Min Act: -0.0000

Data Index: 283085 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1379593 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1414861 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1431546 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.7869. Min Act: -0.0000

Data Index: 556071 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.8210. Min Act: -0.0000

Data Index: 997654 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1748775 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.7802. Min Act: -0.0000

Data Index: 265645 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1571177 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.7316. Min Act: -0.0000

Data Index: 71958 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1699562 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.7975. Min Act: -0.0000

Data Index: 84770 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 1.4685. Min Range: -1.4685

Max Act: 0.6935. Min Act: -0.0000

Data Index: 650089 (The Pile)

Max Activating Token Index: 515