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

Dataset: The Pile

Neuron 3544 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: 3.2256. Min Range: -3.2256

Max Act: 3.2256. Min Act: -0.0000

Data Index: 808158 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.1161. Min Act: -0.0000

Data Index: 41019 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.2543. Min Act: -0.0000

Data Index: 1383554 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.4312. Min Act: -0.0000

Data Index: 437301 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.2115. Min Act: -0.0000

Data Index: 896943 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.2365. Min Act: -0.0000

Data Index: 698210 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.0594. Min Act: -0.0000

Data Index: 1335926 (The Pile)

Max Activating Token Index: 795

Text #7

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.0254. Min Act: -0.0000

Data Index: 166735 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.0290. Min Act: -0.0000

Data Index: 1492825 (The Pile)

Max Activating Token Index: 742

Text #9

Max Range: 3.2256. Min Range: -3.2256

Max Act: 1.9974. Min Act: -0.0000

Data Index: 1592837 (The Pile)

Max Activating Token Index: 428

Text #10

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.4111. Min Act: -0.0000

Data Index: 1325131 (The Pile)

Max Activating Token Index: 915

Text #11

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.0639. Min Act: -0.0000

Data Index: 738305 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.0502. Min Act: -0.0000

Data Index: 210438 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 3.2256. Min Range: -3.2256

Max Act: 1.9761. Min Act: -0.0000

Data Index: 620327 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.2041. Min Act: -0.0000

Data Index: 1260922 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.1016. Min Act: -0.0000

Data Index: 131838 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1599332 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 3.2256. Min Range: -3.2256

Max Act: 1.9048. Min Act: -0.0000

Data Index: 1640848 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 3.2256. Min Range: -3.2256

Max Act: 2.0385. Min Act: -0.0000

Data Index: 978477 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 3.2256. Min Range: -3.2256

Max Act: 1.8935. Min Act: -0.0000

Data Index: 980069 (The Pile)

Max Activating Token Index: 483