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

Dataset: The Pile

Neuron 3935 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1900120 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1742364 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2421. Min Act: -0.0000

Data Index: 531308 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1621746 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1353. Min Act: -0.0000

Data Index: 388318 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1608. Min Act: -0.0000

Data Index: 840007 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1596. Min Act: -0.0000

Data Index: 920766 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1429. Min Act: -0.0000

Data Index: 918211 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1535. Min Act: -0.0000

Data Index: 512076 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1982207 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1464. Min Act: -0.0000

Data Index: 843700 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1456016 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1394. Min Act: -0.0000

Data Index: 82904 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1318. Min Act: -0.0000

Data Index: 997342 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1178. Min Act: -0.0000

Data Index: 555657 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1792491 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1138852 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1100901 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1304. Min Act: -0.0000

Data Index: 785115 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1192. Min Act: -0.0000

Data Index: 589888 (The Pile)

Max Activating Token Index: 693