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

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

Neuron 4776 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.9333. Min Act: -0.0000

Data Index: 20939 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.7713. Min Act: -0.0000

Data Index: 315291 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.5900. Min Act: -0.0000

Data Index: 746047 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.6607. Min Act: -0.0000

Data Index: 1255200 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.7389. Min Act: -0.0000

Data Index: 408703 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.4139. Min Act: -0.0000

Data Index: 125197 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.5179. Min Act: -0.0000

Data Index: 598129 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.5080. Min Act: -0.0000

Data Index: 601371 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.3740. Min Act: -0.0000

Data Index: 837302 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.4955. Min Act: -0.0000

Data Index: 389238 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.2673. Min Act: -0.0000

Data Index: 205676 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.3735. Min Act: -0.0000

Data Index: 1312972 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.3704. Min Act: -0.0000

Data Index: 483663 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.3539. Min Act: -0.0000

Data Index: 1121046 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.3530. Min Act: -0.0000

Data Index: 290261 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.4409. Min Act: -0.0000

Data Index: 248665 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.3284. Min Act: -0.0000

Data Index: 1039425 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.2163. Min Act: -0.0000

Data Index: 574784 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.1988. Min Act: -0.0000

Data Index: 810533 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 2.9333. Min Range: -2.9333

Max Act: 2.1884. Min Act: -0.0000

Data Index: 1019422 (C4 (Web Text))

Max Activating Token Index: 613