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

Dataset: The Pile

Neuron 3874 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1266260 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1697669 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1664428 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1161803 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1750140 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1448437 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2836. Min Act: -0.0000

Data Index: 269988 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2815. Min Act: -0.0000

Data Index: 302854 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2810. Min Act: -0.0000

Data Index: 499450 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2865. Min Act: -0.0000

Data Index: 118461 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2644. Min Act: -0.0000

Data Index: 367724 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2906. Min Act: -0.0000

Data Index: 677160 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2794. Min Act: -0.0000

Data Index: 532562 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2583. Min Act: -0.0000

Data Index: 823543 (The Pile)

Max Activating Token Index: 874

Text #14

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1343150 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1445266 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1827827 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2598. Min Act: -0.0000

Data Index: 600539 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1237423 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 0.3589. Min Range: -0.3589

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1724420 (The Pile)

Max Activating Token Index: 846