Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1996 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3902. Min Act: -0.0000

Data Index: 315452 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3663. Min Act: -0.0000

Data Index: 677219 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1425178 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1690733 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3434. Min Act: -0.0000

Data Index: 880020 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1219427 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3637. Min Act: -0.0000

Data Index: 163382 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3232. Min Act: -0.0000

Data Index: 146809 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3333. Min Act: -0.0000

Data Index: 18261 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1382306 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3437. Min Act: -0.0000

Data Index: 680340 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3072. Min Act: -0.0000

Data Index: 510351 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3194. Min Act: -0.0000

Data Index: 920946 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3376. Min Act: -0.0000

Data Index: 693592 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1977392 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1494141 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3079. Min Act: -0.0000

Data Index: 479746 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3085. Min Act: -0.0000

Data Index: 659330 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1309528 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2988. Min Act: -0.0000

Data Index: 526635 (The Pile)

Max Activating Token Index: 784