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

Dataset: The Pile

Neuron 931 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1939813 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1880982 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1101300 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1312. Min Act: -0.0000

Data Index: 636186 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1237. Min Act: -0.0000

Data Index: 595148 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1253. Min Act: -0.0000

Data Index: 849960 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1977404 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1209. Min Act: -0.0000

Data Index: 431763 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1068655 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1210385 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1818155 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1868526 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1207. Min Act: -0.0000

Data Index: 166705 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1674517 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1463763 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1447232 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1450876 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1010. Min Act: -0.0000

Data Index: 389266 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1073. Min Act: -0.0000

Data Index: 114165 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1276828 (The Pile)

Max Activating Token Index: 88