Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1024 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2860. Min Range: -2.2860

Max Act: 2.1968. Min Act: -0.0000

Data Index: 1257301 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 2.2860. Min Range: -2.2860

Max Act: 2.2860. Min Act: -0.0000

Data Index: 1315895 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 2.2860. Min Range: -2.2860

Max Act: 2.0132. Min Act: -0.0000

Data Index: 170994 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.8039. Min Act: -0.0001

Data Index: 65995 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.9157. Min Act: -0.0000

Data Index: 1307857 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.9360. Min Act: -0.0000

Data Index: 1313382 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.7820. Min Act: -0.0000

Data Index: 445580 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.5819. Min Act: -0.0000

Data Index: 707723 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.7083. Min Act: -0.0000

Data Index: 523309 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.6150. Min Act: -0.0000

Data Index: 476372 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.6510. Min Act: -0.0000

Data Index: 783201 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.6095. Min Act: -0.0001

Data Index: 739507 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.5552. Min Act: -0.0000

Data Index: 756229 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.6381. Min Act: -0.0001

Data Index: 1150590 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.5073. Min Act: -0.0000

Data Index: 267982 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.5464. Min Act: -0.0000

Data Index: 100548 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.5522. Min Act: -0.0000

Data Index: 918078 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.6102. Min Act: -0.0000

Data Index: 619399 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1222495 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 2.2860. Min Range: -2.2860

Max Act: 1.5729. Min Act: -0.0000

Data Index: 921847 (C4 (Web Text))

Max Activating Token Index: 360