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

Dataset: The Pile

Neuron 868 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: 0.4179. Min Range: -0.4179

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1743073 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1141849 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1545223 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2912. Min Act: -0.0000

Data Index: 12054 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2755. Min Act: -0.0000

Data Index: 207934 (The Pile)

Max Activating Token Index: 926

Text #5

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1809183 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2822. Min Act: -0.0000

Data Index: 130051 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1013997 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2868. Min Act: -0.0000

Data Index: 292153 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2712. Min Act: -0.0000

Data Index: 872453 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2570. Min Act: -0.0000

Data Index: 350734 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1140215 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1836652 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1308085 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1891139 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1366442 (The Pile)

Max Activating Token Index: 952

Text #16

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2318. Min Act: -0.0000

Data Index: 209434 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2200. Min Act: -0.0000

Data Index: 739248 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1894536 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.4179. Min Range: -0.4179

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1112124 (The Pile)

Max Activating Token Index: 627