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

Dataset: The Pile

Neuron 125 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1167. Min Range: -1.1167

Max Act: 1.1167. Min Act: -0.0000

Data Index: 229100 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 1.1167. Min Range: -1.1167

Max Act: 1.0219. Min Act: -0.0000

Data Index: 79478 (The Pile)

Max Activating Token Index: 125

Text #2

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1724283 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1511812 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1221775 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1617394 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8120. Min Act: -0.0000

Data Index: 419007 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8455. Min Act: -0.0000

Data Index: 814178 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8623. Min Act: -0.0000

Data Index: 772547 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7662. Min Act: 0.0000

Data Index: 1208047 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1756312 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1798072 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8043. Min Act: -0.0000

Data Index: 360281 (The Pile)

Max Activating Token Index: 794

Text #13

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.8023. Min Act: -0.0000

Data Index: 274330 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7776. Min Act: -0.0000

Data Index: 647259 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7433. Min Act: 0.0001

Data Index: 1822556 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1330860 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7448. Min Act: -0.0000

Data Index: 885618 (The Pile)

Max Activating Token Index: 783

Text #18

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1171461 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 1.1167. Min Range: -1.1167

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1375664 (The Pile)

Max Activating Token Index: 232