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

Dataset: The Pile

Neuron 842 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.8676. Min Act: -0.0000

Data Index: 501656 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1889962 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.5551. Min Act: -0.0000

Data Index: 835488 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3701. Min Act: -0.0000

Data Index: 913273 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1508595 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.4099. Min Act: -0.0000

Data Index: 958253 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1951679 (The Pile)

Max Activating Token Index: 538

Text #7

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1744953 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3631. Min Act: -0.0000

Data Index: 600405 (The Pile)

Max Activating Token Index: 804

Text #9

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3002. Min Act: -0.0000

Data Index: 691369 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1579449 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3595. Min Act: -0.0000

Data Index: 327057 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1847923 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3682. Min Act: -0.0000

Data Index: 590772 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3672. Min Act: -0.0000

Data Index: 948573 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1371704 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1902833 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3404. Min Act: -0.0000

Data Index: 856260 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3154. Min Act: -0.0000

Data Index: 199999 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1564180 (The Pile)

Max Activating Token Index: 760