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

Dataset: The Pile

Neuron 2221 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: 1.3927. Min Range: -1.3927

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1869808 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.2608. Min Act: -0.0000

Data Index: 586095 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.2065. Min Act: -0.0000

Data Index: 216140 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.3094. Min Act: -0.0000

Data Index: 480643 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1974. Min Act: -0.0000

Data Index: 509078 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.2254. Min Act: -0.0000

Data Index: 1214246 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1392. Min Act: -0.0000

Data Index: 219613 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0939. Min Act: -0.0000

Data Index: 402102 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1730140 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1886. Min Act: -0.0000

Data Index: 677673 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1816672 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1748. Min Act: -0.0000

Data Index: 49033 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1967. Min Act: -0.0000

Data Index: 220998 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1825377 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1050856 (The Pile)

Max Activating Token Index: 756

Text #15

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1048672 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1601374 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1247. Min Act: -0.0000

Data Index: 56570 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1078793 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.1317. Min Act: -0.0000

Data Index: 938272 (The Pile)

Max Activating Token Index: 124