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

Dataset: The Pile

Neuron 1204 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: 0.8671. Min Range: -0.8671

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1129382 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1390058 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1578563 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7769. Min Act: -0.0000

Data Index: 491175 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7277. Min Act: -0.0000

Data Index: 58921 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1129107 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7009. Min Act: -0.0000

Data Index: 452799 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1885652 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1120862 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.7034. Min Act: -0.0000

Data Index: 553325 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6972. Min Act: -0.0000

Data Index: 280308 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1795845 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6869. Min Act: -0.0000

Data Index: 239704 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6511. Min Act: -0.0000

Data Index: 117454 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6740. Min Act: -0.0000

Data Index: 416375 (The Pile)

Max Activating Token Index: 143

Text #15

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6845. Min Act: -0.0000

Data Index: 429871 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1414508 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6328. Min Act: -0.0000

Data Index: 864605 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6592. Min Act: -0.0000

Data Index: 91771 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 0.8671. Min Range: -0.8671

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1288859 (The Pile)

Max Activating Token Index: 882