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

Dataset: The Pile

Neuron 1290 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: 0.9306. Min Range: -0.9306

Max Act: 0.9282. Min Act: -0.0000

Data Index: 402535 (The Pile)

Max Activating Token Index: 147

Text #1

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9028. Min Act: -0.0000

Data Index: 538278 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1745793 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1046429 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8140. Min Act: -0.0000

Data Index: 495206 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1689765 (The Pile)

Max Activating Token Index: 9

Text #6

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1825232 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1552314 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1938935 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1475785 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7422. Min Act: -0.0000

Data Index: 943774 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7730. Min Act: 0.0001

Data Index: 702251 (The Pile)

Max Activating Token Index: 606

Text #12

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1600280 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7465. Min Act: -0.0000

Data Index: 178674 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1734799 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6965. Min Act: -0.0000

Data Index: 966103 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8126. Min Act: -0.0000

Data Index: 984759 (The Pile)

Max Activating Token Index: 726

Text #17

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7592. Min Act: -0.0000

Data Index: 926413 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7378. Min Act: -0.0000

Data Index: 743841 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1310692 (The Pile)

Max Activating Token Index: 987