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

Dataset: The Pile

Neuron 4170 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: 1.7602. Min Range: -1.7602

Max Act: 1.7602. Min Act: -0.0000

Data Index: 1124706 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4153. Min Act: -0.0000

Data Index: 45478 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.6216. Min Act: -0.0000

Data Index: 1443056 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3891. Min Act: -0.0000

Data Index: 288645 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3990. Min Act: -0.0000

Data Index: 801471 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1793058 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4202. Min Act: -0.0000

Data Index: 163378 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1598315 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4103. Min Act: -0.0000

Data Index: 1698446 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4083. Min Act: -0.0000

Data Index: 946757 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3610. Min Act: -0.0000

Data Index: 281823 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3440. Min Act: -0.0000

Data Index: 644924 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2880. Min Act: -0.0000

Data Index: 733122 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1925693 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2987. Min Act: -0.0000

Data Index: 783822 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1936123 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1916988 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1612830 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3424. Min Act: -0.0000

Data Index: 1756235 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3247. Min Act: -0.0000

Data Index: 844305 (The Pile)

Max Activating Token Index: 588