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

Dataset: The Pile

Neuron 1067 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: 1.6520. Min Range: -1.6520

Max Act: 1.6520. Min Act: -0.0000

Data Index: 123322 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.5256. Min Act: -0.0000

Data Index: 1313676 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1951267 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.6170. Min Act: -0.0000

Data Index: 958159 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.5074. Min Act: -0.0000

Data Index: 1249187 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1491035 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.4253. Min Act: -0.0000

Data Index: 865090 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.3351. Min Act: -0.0000

Data Index: 437501 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1602186 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2148. Min Act: -0.0000

Data Index: 600887 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1407914 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1961679 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1542. Min Act: -0.0000

Data Index: 963232 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1434611 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1420002 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1268. Min Act: -0.0000

Data Index: 900661 (The Pile)

Max Activating Token Index: 181

Text #16

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1065. Min Act: -0.0000

Data Index: 83971 (The Pile)

Max Activating Token Index: 669

Text #17

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.1079. Min Act: -0.0000

Data Index: 453027 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1872913 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 1.6520. Min Range: -1.6520

Max Act: 1.0512. Min Act: -0.0000

Data Index: 420507 (The Pile)

Max Activating Token Index: 918