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

Dataset: The Pile

Neuron 5090 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1572969 (The Pile)

Max Activating Token Index: 696

Text #1

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1151784 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1238830 (The Pile)

Max Activating Token Index: 180

Text #3

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1429. Min Act: -0.0000

Data Index: 713305 (The Pile)

Max Activating Token Index: 692

Text #4

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1263140 (The Pile)

Max Activating Token Index: 946

Text #5

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1184. Min Act: -0.0000

Data Index: 131110 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1183. Min Act: -0.0000

Data Index: 953440 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1130. Min Act: -0.0000

Data Index: 641356 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1931597 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1163. Min Act: -0.0000

Data Index: 1790117 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1163. Min Act: -0.0000

Data Index: 899830 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1088. Min Act: -0.0000

Data Index: 176884 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1126. Min Act: -0.0000

Data Index: 912439 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1922305 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1470288 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1595165 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1000625 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1280779 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1588751 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1058. Min Act: -0.0000

Data Index: 209737 (The Pile)

Max Activating Token Index: 370