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

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

Neuron 5951 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.9761. Min Act: -0.0000

Data Index: 643641 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.8076. Min Act: -0.0000

Data Index: 1387541 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.8130. Min Act: -0.0000

Data Index: 267944 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.6588. Min Act: -0.0000

Data Index: 856935 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.5837. Min Act: -0.0000

Data Index: 1489615 (Python Code)

Max Activating Token Index: 982

Text #5

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.6413. Min Act: -0.0000

Data Index: 115356 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.6164. Min Act: -0.0000

Data Index: 578025 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.4314. Min Act: -0.0000

Data Index: 70806 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.4585. Min Act: -0.0000

Data Index: 752903 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.2627. Min Act: -0.0000

Data Index: 928369 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.3859. Min Act: -0.0000

Data Index: 390432 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.3944. Min Act: -0.0000

Data Index: 131275 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.3081. Min Act: -0.0000

Data Index: 278364 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.2110. Min Act: -0.0000

Data Index: 742637 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.1832. Min Act: -0.0000

Data Index: 571614 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.1812. Min Act: -0.0000

Data Index: 1340170 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.1814. Min Act: -0.0000

Data Index: 699351 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1068868 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.0138. Min Act: -0.0000

Data Index: 1420595 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 2.9761. Min Range: -2.9761

Max Act: 2.1323. Min Act: -0.0000

Data Index: 605012 (C4 (Web Text))

Max Activating Token Index: 114