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

Dataset: The Pile

Neuron 4909 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: 3.7400. Min Range: -3.7400

Max Act: 3.6905. Min Act: -0.0000

Data Index: 583727 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.4569. Min Act: -0.0000

Data Index: 1198030 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.7400. Min Act: -0.0000

Data Index: 1162694 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.5368. Min Act: -0.0000

Data Index: 851755 (The Pile)

Max Activating Token Index: 877

Text #4

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.0449. Min Act: -0.0000

Data Index: 973549 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.1642. Min Act: -0.0000

Data Index: 1761904 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.1480. Min Act: -0.0000

Data Index: 228442 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.2337. Min Act: -0.0000

Data Index: 627421 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.3245. Min Act: -0.0000

Data Index: 851469 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.0243. Min Act: -0.0000

Data Index: 566148 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.1751. Min Act: -0.0000

Data Index: 1432987 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 3.7400. Min Range: -3.7400

Max Act: 2.9167. Min Act: -0.0000

Data Index: 1802638 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.1910. Min Act: -0.0000

Data Index: 1018626 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 3.7400. Min Range: -3.7400

Max Act: 2.7349. Min Act: -0.0000

Data Index: 393239 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 3.7400. Min Range: -3.7400

Max Act: 2.8254. Min Act: -0.0000

Data Index: 220117 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 3.7400. Min Range: -3.7400

Max Act: 2.8370. Min Act: -0.0000

Data Index: 1481442 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 3.7400. Min Range: -3.7400

Max Act: 2.9628. Min Act: -0.0000

Data Index: 430623 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 3.7400. Min Range: -3.7400

Max Act: 2.7791. Min Act: -0.0000

Data Index: 1327980 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 3.7400. Min Range: -3.7400

Max Act: 2.9452. Min Act: -0.0000

Data Index: 561215 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 3.7400. Min Range: -3.7400

Max Act: 2.7506. Min Act: -0.0000

Data Index: 980458 (The Pile)

Max Activating Token Index: 595