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

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

Neuron 1105 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3784. Min Range: -5.3784

Max Act: 5.0857. Min Act: -0.0000

Data Index: 715059 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 5.3784. Min Range: -5.3784

Max Act: 5.3784. Min Act: -0.0000

Data Index: 718616 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.8746. Min Act: -0.0000

Data Index: 900170 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 5.3784. Min Range: -5.3784

Max Act: 5.0247. Min Act: -0.0000

Data Index: 789705 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 5.3784. Min Range: -5.3784

Max Act: 5.1314. Min Act: -0.0000

Data Index: 1261970 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.7944. Min Act: -0.0000

Data Index: 246701 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.8942. Min Act: -0.0000

Data Index: 58818 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.6005. Min Act: -0.0000

Data Index: 1150666 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.8259. Min Act: -0.0000

Data Index: 1226075 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.7839. Min Act: -0.0000

Data Index: 353113 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.7725. Min Act: -0.0000

Data Index: 880888 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.7891. Min Act: -0.0000

Data Index: 1048297 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.5882. Min Act: -0.0000

Data Index: 565553 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.7657. Min Act: -0.0000

Data Index: 150121 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.2547. Min Act: -0.0000

Data Index: 389490 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.9067. Min Act: -0.0000

Data Index: 509074 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.6660. Min Act: -0.0000

Data Index: 1649227 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.5500. Min Act: -0.0000

Data Index: 1226665 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.7592. Min Act: -0.0000

Data Index: 1564092 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 5.3784. Min Range: -5.3784

Max Act: 4.6820. Min Act: -0.0000

Data Index: 443578 (C4 (Web Text))

Max Activating Token Index: 180