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

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

Neuron 4903 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.6478. Min Act: -0.0000

Data Index: 1273585 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.7491. Min Act: -0.0000

Data Index: 992235 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.4241. Min Act: -0.0000

Data Index: 710895 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.9094. Min Act: -0.0000

Data Index: 592615 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.5762. Min Act: -0.0000

Data Index: 331960 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.7381. Min Act: -0.0000

Data Index: 1205450 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.5724. Min Act: -0.0000

Data Index: 444266 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.4249. Min Act: -0.0000

Data Index: 910499 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.4889. Min Act: -0.0000

Data Index: 792019 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.2466. Min Act: -0.0000

Data Index: 259791 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.4108. Min Act: -0.0000

Data Index: 973175 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.2147. Min Act: -0.0000

Data Index: 774878 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.2062. Min Act: -0.0000

Data Index: 1262496 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 2.9094. Min Range: -2.9094

Max Act: 1.9482. Min Act: -0.0000

Data Index: 669251 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.0647. Min Act: -0.0000

Data Index: 1014517 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.0439. Min Act: -0.0000

Data Index: 477175 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 2.9094. Min Range: -2.9094

Max Act: 1.9290. Min Act: -0.0000

Data Index: 1242198 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 2.9094. Min Range: -2.9094

Max Act: 1.9816. Min Act: -0.0000

Data Index: 1242713 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 2.9094. Min Range: -2.9094

Max Act: 1.9643. Min Act: -0.0000

Data Index: 857679 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.0414. Min Act: -0.0000

Data Index: 1210031 (C4 (Web Text))

Max Activating Token Index: 2