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

Dataset: The Pile

Neuron 1488 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1919. Min Range: -1.1919

Max Act: 1.1919. Min Act: -0.0000

Data Index: 774723 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 1.1919. Min Range: -1.1919

Max Act: 1.0789. Min Act: -0.0000

Data Index: 919523 (The Pile)

Max Activating Token Index: 235

Text #2

Max Range: 1.1919. Min Range: -1.1919

Max Act: 1.0462. Min Act: -0.0000

Data Index: 964653 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 1.1919. Min Range: -1.1919

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1346112 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9720. Min Act: -0.0000

Data Index: 173337 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1476987 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9424. Min Act: -0.0000

Data Index: 469811 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9127. Min Act: -0.0000

Data Index: 222834 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1138114 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9003. Min Act: -0.0000

Data Index: 789827 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1278792 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9140. Min Act: -0.0000

Data Index: 793532 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1341473 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.7433. Min Act: -0.0000

Data Index: 865397 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8983. Min Act: -0.0000

Data Index: 64892 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1430754 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8992. Min Act: -0.0000

Data Index: 607098 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1008411 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8931. Min Act: -0.0000

Data Index: 140994 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 1.1919. Min Range: -1.1919

Max Act: 0.8940. Min Act: -0.0000

Data Index: 19247 (The Pile)

Max Activating Token Index: 706