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

Dataset: The Pile

Neuron 3285 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: 0.5650. Min Range: -0.5650

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1659926 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4983. Min Act: -0.0000

Data Index: 800943 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1772978 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.5238. Min Act: -0.0000

Data Index: 769754 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4619. Min Act: -0.0000

Data Index: 776991 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1273803 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4451. Min Act: -0.0000

Data Index: 146409 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4739. Min Act: -0.0000

Data Index: 339221 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1930688 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.5194. Min Act: -0.0000

Data Index: 455753 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1525434 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4199. Min Act: -0.0000

Data Index: 127377 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4374. Min Act: -0.0000

Data Index: 855526 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1161568 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4417. Min Act: -0.0000

Data Index: 845731 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4467. Min Act: -0.0000

Data Index: 637312 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4331. Min Act: -0.0000

Data Index: 722662 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.3818. Min Act: -0.0000

Data Index: 771861 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1969128 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 0.5650. Min Range: -0.5650

Max Act: 0.4381. Min Act: -0.0000

Data Index: 904307 (The Pile)

Max Activating Token Index: 677