Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2248 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1614772 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1532635 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6206. Min Act: -0.0000

Data Index: 420532 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.7805. Min Act: -0.0000

Data Index: 467370 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6965. Min Act: -0.0000

Data Index: 470220 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1361401 (The Pile)

Max Activating Token Index: 514

Text #6

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1474293 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.7159. Min Act: -0.0000

Data Index: 374647 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1464986 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1377382 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1872035 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6208. Min Act: -0.0000

Data Index: 597044 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1427850 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5963. Min Act: -0.0000

Data Index: 303410 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1543892 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1486314 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1453154 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5613. Min Act: -0.0000

Data Index: 348020 (The Pile)

Max Activating Token Index: 538

Text #18

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1176696 (The Pile)

Max Activating Token Index: 47

Text #19

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1226957 (The Pile)

Max Activating Token Index: 425