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

Dataset: The Pile

Neuron 4549 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0351. Min Range: -1.0351

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1405163 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9401. Min Act: -0.0000

Data Index: 177594 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1071932 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8864. Min Act: -0.0001

Data Index: 268696 (The Pile)

Max Activating Token Index: 67

Text #4

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8538. Min Act: -0.0000

Data Index: 372865 (The Pile)

Max Activating Token Index: 859

Text #5

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8883. Min Act: -0.0000

Data Index: 383491 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7958. Min Act: -0.0000

Data Index: 441256 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1523506 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1754962 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1065885 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7872. Min Act: -0.0000

Data Index: 689365 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8034. Min Act: -0.0000

Data Index: 758756 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9126. Min Act: -0.0000

Data Index: 773568 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1685603 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7881. Min Act: -0.0000

Data Index: 553576 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7623. Min Act: -0.0000

Data Index: 466178 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8078. Min Act: -0.0001

Data Index: 1356032 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8338. Min Act: -0.0000

Data Index: 407994 (The Pile)

Max Activating Token Index: 934

Text #18

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1068913 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1253539 (The Pile)

Max Activating Token Index: 738