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

Dataset: The Pile

Neuron 2742 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: 1.1146. Min Range: -1.1146

Max Act: 0.8387. Min Act: -0.0000

Data Index: 848386 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1538899 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 1.1146. Min Range: -1.1146

Max Act: 1.0845. Min Act: -0.0000

Data Index: 807940 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 1.1146. Min Range: -1.1146

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1078183 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1624845 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1464302 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8291. Min Act: -0.0000

Data Index: 45890 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 1.1146. Min Range: -1.1146

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1534209 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1901743 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8200. Min Act: -0.0000

Data Index: 333320 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8182. Min Act: -0.0000

Data Index: 604725 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1024897 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8111. Min Act: -0.0000

Data Index: 1006766 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8245. Min Act: -0.0000

Data Index: 826761 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.7914. Min Act: -0.0000

Data Index: 947614 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1679680 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8524. Min Act: -0.0000

Data Index: 138888 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8112. Min Act: -0.0000

Data Index: 177035 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8029. Min Act: -0.0000

Data Index: 722456 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 1.1146. Min Range: -1.1146

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1626389 (The Pile)

Max Activating Token Index: 580