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

Dataset: The Pile

Neuron 990 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: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0000

Data Index: 864038 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7799. Min Act: -0.0000

Data Index: 480321 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1207890 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1338956 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7677. Min Act: -0.0000

Data Index: 365112 (The Pile)

Max Activating Token Index: 497

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1222750 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1764192 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1789532 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6811. Min Act: -0.0000

Data Index: 246575 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6719. Min Act: -0.0000

Data Index: 795500 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6606. Min Act: -0.0000

Data Index: 497005 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6606. Min Act: -0.0000

Data Index: 732323 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1062814 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1470842 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6362. Min Act: -0.0000

Data Index: 352245 (The Pile)

Max Activating Token Index: 913

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6255. Min Act: -0.0000

Data Index: 356969 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1968558 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6554. Min Act: -0.0000

Data Index: 321495 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6956. Min Act: -0.0000

Data Index: 294860 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6370. Min Act: -0.0000

Data Index: 799012 (The Pile)

Max Activating Token Index: 574