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

Dataset: The Pile

Neuron 1812 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: 1.8179. Min Range: -1.8179

Max Act: 1.8179. Min Act: -0.0000

Data Index: 1047930 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.6423. Min Act: -0.0000

Data Index: 1333634 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.5509. Min Act: -0.0000

Data Index: 1835220 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.5228. Min Act: -0.0001

Data Index: 191191 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1673700 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1519059 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.4464. Min Act: -0.0000

Data Index: 1035400 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1893148 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.2144. Min Act: -0.0000

Data Index: 1259530 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1150631 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3495. Min Act: -0.0000

Data Index: 1475003 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3882. Min Act: -0.0000

Data Index: 802574 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3326. Min Act: -0.0000

Data Index: 919867 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3572. Min Act: -0.0000

Data Index: 440509 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1581305 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3179. Min Act: -0.0000

Data Index: 343202 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1324825 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.1304. Min Act: -0.0000

Data Index: 585360 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1308343 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3070. Min Act: -0.0000

Data Index: 705929 (The Pile)

Max Activating Token Index: 1020