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

Dataset: The Pile

Neuron 3420 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: 1.4104. Min Range: -1.4104

Max Act: 1.4104. Min Act: -0.0000

Data Index: 965569 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.4072. Min Act: -0.0000

Data Index: 730851 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3393. Min Act: -0.0000

Data Index: 977931 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3231. Min Act: -0.0000

Data Index: 838084 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1478994 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2845. Min Act: -0.0000

Data Index: 130112 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2377. Min Act: -0.0000

Data Index: 52742 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2574. Min Act: -0.0000

Data Index: 1154774 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2396. Min Act: -0.0000

Data Index: 1219338 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1919527 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1510807 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1236050 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1359941 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1858. Min Act: -0.0000

Data Index: 696211 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1473277 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1940368 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2087. Min Act: -0.0000

Data Index: 359507 (The Pile)

Max Activating Token Index: 317

Text #17

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1306. Min Act: -0.0001

Data Index: 1818850 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1667621 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0847. Min Act: -0.0000

Data Index: 282798 (The Pile)

Max Activating Token Index: 1019