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

Dataset: The Pile

Neuron 5055 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.8048. Min Act: -0.0000

Data Index: 595811 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1291778 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.2441. Min Act: -0.0000

Data Index: 759255 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1310507 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1904877 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1659569 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1682473 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.9145. Min Act: -0.0000

Data Index: 347194 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1863636 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1217058 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.9156. Min Act: 0.0000

Data Index: 1875242 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.9630. Min Act: -0.0000

Data Index: 645183 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.8968. Min Act: -0.0000

Data Index: 842426 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.9405. Min Act: -0.0000

Data Index: 866152 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.8859. Min Act: 0.0000

Data Index: 108843 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.8226. Min Act: -0.0000

Data Index: 872442 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1284007 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1562666 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1205737 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 1.8048. Min Range: -1.8048

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1034885 (The Pile)

Max Activating Token Index: 217