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

Dataset: The Pile

Neuron 513 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1831183 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.6142. Min Act: -0.0000

Data Index: 536995 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1078259 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3564. Min Act: -0.0000

Data Index: 962905 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3545. Min Act: -0.0000

Data Index: 87614 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1111684 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2814. Min Act: -0.0000

Data Index: 1170298 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1519292 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1235912 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1788. Min Act: -0.0000

Data Index: 1270426 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1807696 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2154. Min Act: -0.0000

Data Index: 216734 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1737271 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.2011. Min Act: -0.0000

Data Index: 1146541 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1904. Min Act: -0.0000

Data Index: 202310 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.1889. Min Act: -0.0000

Data Index: 1721019 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1163318 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.0366. Min Act: -0.0000

Data Index: 575594 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 1.6142. Min Range: -1.6142

Max Act: 0.9546. Min Act: -0.0000

Data Index: 711322 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 1.6142. Min Range: -1.6142

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1246785 (The Pile)

Max Activating Token Index: 273