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

Dataset: The Pile

Neuron 2703 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: 0.7328. Min Range: -0.7328

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1466074 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.7328. Min Act: -0.0000

Data Index: 417202 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1021298 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5855. Min Act: -0.0000

Data Index: 507166 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5492. Min Act: -0.0000

Data Index: 475562 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5378. Min Act: -0.0000

Data Index: 904816 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5689. Min Act: -0.0000

Data Index: 635522 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5538. Min Act: -0.0000

Data Index: 554007 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1097606 (The Pile)

Max Activating Token Index: 861

Text #9

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5581. Min Act: -0.0000

Data Index: 82730 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1782329 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1864982 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1835261 (The Pile)

Max Activating Token Index: 619

Text #13

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5174. Min Act: -0.0000

Data Index: 653144 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1118287 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1414258 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.4959. Min Act: -0.0000

Data Index: 415317 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1499284 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1813593 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.4901. Min Act: -0.0000

Data Index: 687340 (The Pile)

Max Activating Token Index: 718