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

Dataset: The Pile

Neuron 1261 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3012. Min Range: -3.3012

Max Act: 3.3012. Min Act: -0.0000

Data Index: 1768945 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.7327. Min Act: -0.0000

Data Index: 463956 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 3.3012. Min Range: -3.3012

Max Act: 3.2913. Min Act: -0.0000

Data Index: 1183221 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.5214. Min Act: -0.0000

Data Index: 894438 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.3840. Min Act: -0.0000

Data Index: 849512 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1934. Min Act: -0.0000

Data Index: 829370 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.3548. Min Act: -0.0000

Data Index: 1947189 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.2408. Min Act: -0.0000

Data Index: 547697 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.2967. Min Act: -0.0000

Data Index: 144627 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.4474. Min Act: -0.0000

Data Index: 618742 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1373. Min Act: -0.0000

Data Index: 809815 (The Pile)

Max Activating Token Index: 711

Text #11

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.2598. Min Act: -0.0000

Data Index: 1705924 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.3544. Min Act: -0.0000

Data Index: 1743800 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.2170. Min Act: -0.0000

Data Index: 1631876 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1123. Min Act: -0.0000

Data Index: 316222 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1589. Min Act: -0.0000

Data Index: 1258221 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 3.3012. Min Range: -3.3012

Max Act: 1.8945. Min Act: -0.0000

Data Index: 883538 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1005615 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1037. Min Act: -0.0000

Data Index: 1792606 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.0777. Min Act: -0.0000

Data Index: 852720 (The Pile)

Max Activating Token Index: 1002