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

Dataset: The Pile

Neuron 2619 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.5798. Min Act: -0.0000

Data Index: 769474 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.4447. Min Act: -0.0000

Data Index: 765504 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.3496. Min Act: -0.0000

Data Index: 1977724 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.2281. Min Act: -0.0000

Data Index: 1180533 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1809. Min Act: -0.0000

Data Index: 326659 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.2719. Min Act: -0.0000

Data Index: 800657 (The Pile)

Max Activating Token Index: 821

Text #6

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1705. Min Act: -0.0000

Data Index: 411547 (The Pile)

Max Activating Token Index: 547

Text #7

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.0218. Min Act: -0.0000

Data Index: 405894 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1369791 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1759. Min Act: -0.0000

Data Index: 443595 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1107684 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1366. Min Act: -0.0000

Data Index: 114859 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1313. Min Act: -0.0001

Data Index: 977793 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1644. Min Act: -0.0000

Data Index: 1967207 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1956. Min Act: -0.0000

Data Index: 1798805 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1991754 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.0423. Min Act: -0.0000

Data Index: 749791 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1253068 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.1434. Min Act: 0.0000

Data Index: 72138 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 1.5798. Min Range: -1.5798

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1883479 (The Pile)

Max Activating Token Index: 484