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

Dataset: The Pile

Neuron 1978 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.4212. Min Act: -0.0000

Data Index: 480620 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.1825. Min Act: -0.0000

Data Index: 599337 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1322480 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1637599 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0451. Min Act: -0.0000

Data Index: 503958 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0890. Min Act: -0.0000

Data Index: 588629 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0314. Min Act: -0.0000

Data Index: 892392 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1492916 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9335. Min Act: -0.0000

Data Index: 226092 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1847702 (The Pile)

Max Activating Token Index: 983

Text #10

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1009462 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9908. Min Act: -0.0000

Data Index: 754677 (The Pile)

Max Activating Token Index: 928

Text #12

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9741. Min Act: -0.0000

Data Index: 703190 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1040133 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.8641. Min Act: -0.0000

Data Index: 196008 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9252. Min Act: -0.0000

Data Index: 890015 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1965737 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1182253 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1334582 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1283012 (The Pile)

Max Activating Token Index: 163