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

Dataset: The Pile

Neuron 832 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: 1.7301. Min Range: -1.7301

Max Act: 1.5006. Min Act: -0.0000

Data Index: 263090 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.0000

Data Index: 832310 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.5759. Min Act: -0.0000

Data Index: 1485012 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.4073. Min Act: -0.0000

Data Index: 506535 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1000901 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.4367. Min Act: -0.0000

Data Index: 1520799 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.4623. Min Act: -0.0000

Data Index: 872820 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.3745. Min Act: -0.0000

Data Index: 1239484 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.4860. Min Act: -0.0000

Data Index: 294414 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.4334. Min Act: -0.0000

Data Index: 41775 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1220362 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.4052. Min Act: -0.0000

Data Index: 734282 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1588020 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1545307 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.4603. Min Act: -0.0000

Data Index: 377027 (The Pile)

Max Activating Token Index: 558

Text #15

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.0905. Min Act: -0.0000

Data Index: 849521 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1075045 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.2025. Min Act: -0.0000

Data Index: 693845 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1656325 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.3462. Min Act: -0.0000

Data Index: 199373 (The Pile)

Max Activating Token Index: 431