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

Dataset: The Pile

Neuron 4264 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: 1.3931. Min Range: -1.3931

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1085388 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.3931. Min Range: -1.3931

Max Act: 1.2272. Min Act: -0.0000

Data Index: 584866 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1394163 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.9553. Min Act: -0.0000

Data Index: 358474 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1166864 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1093140 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.7823. Min Act: -0.0000

Data Index: 825000 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8230. Min Act: -0.0000

Data Index: 518815 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8412. Min Act: -0.0000

Data Index: 320073 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1600993 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8228. Min Act: -0.0000

Data Index: 811611 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1336678 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8123. Min Act: -0.0000

Data Index: 830030 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8529. Min Act: -0.0000

Data Index: 147960 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.7878. Min Act: -0.0000

Data Index: 262298 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8031. Min Act: -0.0000

Data Index: 142209 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.7574. Min Act: -0.0000

Data Index: 954820 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1622886 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.7684. Min Act: -0.0000

Data Index: 658247 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 1.3931. Min Range: -1.3931

Max Act: 0.8907. Min Act: -0.0000

Data Index: 786720 (The Pile)

Max Activating Token Index: 640