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

Dataset: The Pile

Neuron 3565 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: 0.8179. Min Range: -0.8179

Max Act: 0.8069. Min Act: -0.0000

Data Index: 531011 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1922435 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1318032 (The Pile)

Max Activating Token Index: 671

Text #3

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1345528 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7088. Min Act: -0.0000

Data Index: 11340 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1879263 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6725. Min Act: -0.0000

Data Index: 523083 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1179043 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1452702 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1511308 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5938. Min Act: -0.0000

Data Index: 526528 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1521221 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1824080 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1103885 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1625950 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1402688 (The Pile)

Max Activating Token Index: 463

Text #16

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5801. Min Act: -0.0000

Data Index: 515846 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5544. Min Act: -0.0000

Data Index: 200972 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5060. Min Act: -0.0000

Data Index: 540050 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1521198 (The Pile)

Max Activating Token Index: 432