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

Dataset: The Pile

Neuron 1931 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2292. Min Range: -1.2292

Max Act: 1.2292. Min Act: -0.0000

Data Index: 1640343 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 1.2292. Min Range: -1.2292

Max Act: 1.0094. Min Act: -0.0000

Data Index: 557296 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 1.2292. Min Range: -1.2292

Max Act: 1.0336. Min Act: -0.0000

Data Index: 895156 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8964. Min Act: -0.0000

Data Index: 634315 (The Pile)

Max Activating Token Index: 691

Text #4

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.9225. Min Act: -0.0000

Data Index: 935733 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.9444. Min Act: -0.0000

Data Index: 984946 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.7779. Min Act: -0.0000

Data Index: 602543 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 1.2292. Min Range: -1.2292

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1456523 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1447120 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1083366 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1916289 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.9149. Min Act: -0.0000

Data Index: 110333 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8131. Min Act: -0.0000

Data Index: 160812 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8749. Min Act: -0.0000

Data Index: 26247 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1503210 (The Pile)

Max Activating Token Index: 988

Text #15

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8172. Min Act: -0.0000

Data Index: 26070 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8376. Min Act: -0.0000

Data Index: 809959 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1425176 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8631. Min Act: -0.0000

Data Index: 646029 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 1.2292. Min Range: -1.2292

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1515287 (The Pile)

Max Activating Token Index: 897