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

Dataset: The Pile

Neuron 2413 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.3026. Min Act: -0.0000

Data Index: 700140 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2878. Min Act: -0.0000

Data Index: 821315 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2678. Min Act: -0.0000

Data Index: 212703 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1633311 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2676. Min Act: -0.0000

Data Index: 92997 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2460. Min Act: -0.0000

Data Index: 239288 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2366. Min Act: -0.0000

Data Index: 450823 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2276. Min Act: -0.0000

Data Index: 898812 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2251. Min Act: -0.0000

Data Index: 259895 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1545716 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1818325 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.1983. Min Act: -0.0000

Data Index: 709963 (The Pile)

Max Activating Token Index: 320

Text #12

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1705612 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1204623 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1250100 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1511232 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1322894 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2196. Min Act: -0.0000

Data Index: 40833 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1494336 (The Pile)

Max Activating Token Index: 193

Text #19

Max Range: 0.3026. Min Range: -0.3026

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1745892 (The Pile)

Max Activating Token Index: 272