Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1372 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1588. Min Range: -2.1588

Max Act: 2.1588. Min Act: -0.0000

Data Index: 534522 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.8896. Min Act: -0.0000

Data Index: 120561 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1330008 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.7281. Min Act: -0.0000

Data Index: 165005 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.7977. Min Act: -0.0000

Data Index: 429349 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 2.1588. Min Range: -2.1588

Max Act: 2.0129. Min Act: -0.0000

Data Index: 1084289 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.7079. Min Act: -0.0000

Data Index: 475497 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.7081. Min Act: -0.0000

Data Index: 646227 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.7814. Min Act: -0.0000

Data Index: 326259 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.6974. Min Act: -0.0000

Data Index: 147503 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.6418. Min Act: -0.0000

Data Index: 850819 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.4712. Min Act: -0.0000

Data Index: 719456 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.5271. Min Act: -0.0000

Data Index: 183952 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.6090. Min Act: -0.0000

Data Index: 692217 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.5793. Min Act: -0.0000

Data Index: 410602 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.7874. Min Act: -0.0000

Data Index: 1157568 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.5955. Min Act: -0.0000

Data Index: 109734 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.2865. Min Act: -0.0000

Data Index: 791072 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.6096. Min Act: -0.0000

Data Index: 90973 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 2.1588. Min Range: -2.1588

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1342377 (C4 (Web Text))

Max Activating Token Index: 952