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

Dataset: The Pile

Neuron 1458 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.2720. Min Act: -0.0000

Data Index: 728009 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.1280. Min Act: -0.0000

Data Index: 972431 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1120565 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1144526 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.0031. Min Act: -0.0000

Data Index: 971971 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1263673 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1640322 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1139597 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9606. Min Act: -0.0000

Data Index: 533670 (The Pile)

Max Activating Token Index: 908

Text #9

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1107618 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1766939 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1862164 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1778671 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9451. Min Act: -0.0000

Data Index: 997569 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1839058 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9849. Min Act: -0.0000

Data Index: 806604 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1473998 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9347. Min Act: -0.0000

Data Index: 736667 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1666355 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1166574 (The Pile)

Max Activating Token Index: 234