Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3349 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9487. Min Act: -0.0000

Data Index: 392055 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8981. Min Act: -0.0000

Data Index: 224491 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1538752 (The Pile)

Max Activating Token Index: 74

Text #3

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1891080 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8726. Min Act: -0.0000

Data Index: 432012 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9561. Min Act: -0.0000

Data Index: 662627 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8842. Min Act: -0.0000

Data Index: 367712 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1366753 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1626135 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8380. Min Act: -0.0000

Data Index: 693251 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1187639 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8055. Min Act: -0.0000

Data Index: 637304 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8126. Min Act: -0.0000

Data Index: 649702 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7662. Min Act: -0.0000

Data Index: 889600 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1828302 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1980924 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1941899 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7423. Min Act: -0.0000

Data Index: 46986 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1960970 (The Pile)

Max Activating Token Index: 967

Text #19

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1880349 (The Pile)

Max Activating Token Index: 49