Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1873 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1851299 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2213. Min Act: -0.0000

Data Index: 571919 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2263. Min Act: -0.0000

Data Index: 260620 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2217. Min Act: -0.0000

Data Index: 894254 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1050180 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2114. Min Act: -0.0000

Data Index: 997437 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2062. Min Act: -0.0000

Data Index: 402441 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1955. Min Act: -0.0000

Data Index: 517941 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.2024. Min Act: -0.0000

Data Index: 764783 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1104085 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1871. Min Act: -0.0000

Data Index: 989114 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1387424 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1664. Min Act: -0.0000

Data Index: 658849 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1760. Min Act: -0.0000

Data Index: 502366 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1207329 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1809. Min Act: -0.0000

Data Index: 815543 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1759. Min Act: -0.0000

Data Index: 645493 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1406465 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1671. Min Act: -0.0000

Data Index: 229251 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 0.2450. Min Range: -0.2450

Max Act: 0.1453. Min Act: -0.0000

Data Index: 241672 (The Pile)

Max Activating Token Index: 538