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

Dataset: The Pile

Neuron 1447 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: 1.3069. Min Range: -1.3069

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1016901 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2241. Min Act: -0.0000

Data Index: 305432 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1626581 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2841. Min Act: -0.0000

Data Index: 519721 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2341. Min Act: -0.0000

Data Index: 845611 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1891489 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2706. Min Act: -0.0000

Data Index: 1413955 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1719144 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1200055 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1264275 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1283412 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1138492 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1222210 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1356416 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1926113 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.1150. Min Act: -0.0000

Data Index: 1525368 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.2074. Min Act: -0.0000

Data Index: 425841 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.0674. Min Act: -0.0000

Data Index: 682896 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.0541. Min Act: -0.0000

Data Index: 522070 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 1.3069. Min Range: -1.3069

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1913304 (The Pile)

Max Activating Token Index: 597