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

Dataset: The Pile

Neuron 3801 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6797. Min Act: -0.0000

Data Index: 291231 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6381. Min Act: -0.0000

Data Index: 233408 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1340623 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6435. Min Act: -0.0000

Data Index: 345141 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6979. Min Act: -0.0000

Data Index: 619076 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6514. Min Act: -0.0000

Data Index: 869520 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1881776 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1468296 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1518612 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1722253 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1834592 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1212705 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1451856 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1447706 (The Pile)

Max Activating Token Index: 95

Text #14

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1272905 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1877903 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5732. Min Act: -0.0000

Data Index: 253400 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1405135 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5853. Min Act: -0.0000

Data Index: 52484 (The Pile)

Max Activating Token Index: 309

Text #19

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1876666 (The Pile)

Max Activating Token Index: 263