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

Dataset: The Pile

Neuron 1151 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.3054. Min Act: -0.0000

Data Index: 407011 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1642220 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1131700 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1375316 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2297. Min Act: -0.0000

Data Index: 262422 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2505. Min Act: -0.0000

Data Index: 333997 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2450. Min Act: -0.0000

Data Index: 556083 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1638422 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1246111 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1715. Min Act: -0.0000

Data Index: 463389 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2049. Min Act: -0.0000

Data Index: 86441 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1385791 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1229733 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2220. Min Act: -0.0000

Data Index: 459723 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1964938 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1427419 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2023. Min Act: -0.0000

Data Index: 383230 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1095217 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1974342 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 0.3054. Min Range: -0.3054

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1334915 (The Pile)

Max Activating Token Index: 364