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

Dataset: The Pile

Neuron 1453 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: 1.2153. Min Range: -1.2153

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1879340 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.1860. Min Act: 0.0000

Data Index: 86338 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1298073 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1087389 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.0554. Min Act: -0.0000

Data Index: 88972 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1917227 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1587775 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.1437. Min Act: -0.0000

Data Index: 697662 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.0093. Min Act: -0.0000

Data Index: 113384 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.0735. Min Act: -0.0000

Data Index: 858554 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.0043. Min Act: -0.0000

Data Index: 335638 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.1263. Min Act: 0.0000

Data Index: 1289423 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.0407. Min Act: -0.0000

Data Index: 196446 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.0984. Min Act: -0.0000

Data Index: 907438 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1362188 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.9634. Min Act: -0.0000

Data Index: 652838 (The Pile)

Max Activating Token Index: 865

Text #16

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.9556. Min Act: -0.0000

Data Index: 151296 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 1.2153. Min Range: -1.2153

Max Act: 1.0051. Min Act: 0.0000

Data Index: 857823 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.9420. Min Act: -0.0000

Data Index: 801143 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 1.2153. Min Range: -1.2153

Max Act: 0.9881. Min Act: -0.0000

Data Index: 360835 (The Pile)

Max Activating Token Index: 1000