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

Dataset: The Pile

Neuron 1157 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: 1.8413. Min Range: -1.8413

Max Act: 1.8413. Min Act: -0.0000

Data Index: 1306895 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.7935. Min Act: -0.0000

Data Index: 1381992 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.6794. Min Act: -0.0000

Data Index: 207770 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.6692. Min Act: -0.0000

Data Index: 1446644 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4496. Min Act: -0.0000

Data Index: 814083 (The Pile)

Max Activating Token Index: 972

Text #5

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3555. Min Act: -0.0000

Data Index: 365199 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3181. Min Act: -0.0000

Data Index: 608444 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.2231. Min Act: -0.0000

Data Index: 516578 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3137. Min Act: -0.0000

Data Index: 303289 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.2586. Min Act: -0.0000

Data Index: 966203 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.1820. Min Act: -0.0000

Data Index: 1735754 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.1800. Min Act: -0.0000

Data Index: 309010 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.2416. Min Act: -0.0000

Data Index: 616293 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.2300. Min Act: -0.0000

Data Index: 1240985 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1715886 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1947894 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1422703 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1368867 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.2389. Min Act: -0.0000

Data Index: 984740 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.2767. Min Act: -0.0000

Data Index: 35826 (The Pile)

Max Activating Token Index: 77