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

Dataset: The Pile

Neuron 303 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.5025. Min Act: -0.0000

Data Index: 1178395 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.3273. Min Act: -0.0000

Data Index: 600121 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.3726. Min Act: -0.0000

Data Index: 964420 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.2576. Min Act: -0.0000

Data Index: 1604238 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1619180 (The Pile)

Max Activating Token Index: 151

Text #5

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.2216. Min Act: -0.0000

Data Index: 497814 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1656622 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1190250 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.0976. Min Act: -0.0000

Data Index: 1455091 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1520108 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.1189. Min Act: -0.0000

Data Index: 654248 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.0219. Min Act: -0.0000

Data Index: 604923 (The Pile)

Max Activating Token Index: 927

Text #12

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.2343. Min Act: -0.0000

Data Index: 514349 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.0582. Min Act: -0.0000

Data Index: 915383 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1094737 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.0157. Min Act: -0.0000

Data Index: 160550 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1112700 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1476612 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 1.5025. Min Range: -1.5025

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1997033 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 1.5025. Min Range: -1.5025

Max Act: 0.9893. Min Act: -0.0000

Data Index: 531751 (The Pile)

Max Activating Token Index: 186