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

Dataset: The Pile

Neuron 1940 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: 1.6461. Min Range: -1.6461

Max Act: 1.6461. Min Act: -0.0000

Data Index: 795089 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1886215 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.4230. Min Act: -0.0000

Data Index: 1146545 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3708. Min Act: -0.0000

Data Index: 90734 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.4142. Min Act: -0.0000

Data Index: 259031 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3972. Min Act: -0.0000

Data Index: 756576 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1212801 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1407211 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1287855 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2961. Min Act: -0.0000

Data Index: 476927 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1800972 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1029524 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1700927 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2007. Min Act: -0.0000

Data Index: 122819 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1753536 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1947. Min Act: -0.0000

Data Index: 380930 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2068. Min Act: -0.0000

Data Index: 714663 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1047122 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1690. Min Act: -0.0000

Data Index: 1912434 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1612. Min Act: -0.0000

Data Index: 136495 (The Pile)

Max Activating Token Index: 568