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

Dataset: The Pile

Neuron 2870 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.2485. Min Act: -0.0000

Data Index: 1746346 (The Pile)

Max Activating Token Index: 810

Text #1

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.5724. Min Act: -0.0000

Data Index: 671531 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.2853. Min Act: -0.0000

Data Index: 490318 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.2304. Min Act: -0.0000

Data Index: 1994109 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.2675. Min Act: -0.0000

Data Index: 922935 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.2569. Min Act: -0.0000

Data Index: 1564959 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.9180. Min Act: -0.0000

Data Index: 1026872 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.1549. Min Act: -0.0000

Data Index: 543865 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.9033. Min Act: -0.0000

Data Index: 1808261 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.7983. Min Act: -0.0000

Data Index: 884314 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.0763. Min Act: -0.0000

Data Index: 1342876 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.9524. Min Act: -0.0000

Data Index: 1807207 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1287939 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.9840. Min Act: -0.0000

Data Index: 173174 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.6123. Min Act: -0.0000

Data Index: 468149 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.9059. Min Act: -0.0000

Data Index: 1463431 (The Pile)

Max Activating Token Index: 782

Text #16

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.7068. Min Act: -0.0000

Data Index: 830915 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.9243. Min Act: -0.0000

Data Index: 1173349 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.4211. Min Act: -0.0000

Data Index: 1634364 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 3.2485. Min Range: -3.2485

Max Act: 1.6923. Min Act: -0.0000

Data Index: 302490 (The Pile)

Max Activating Token Index: 569