Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3396 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1065. Min Act: -0.0001

Data Index: 492070 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0967. Min Act: -0.0001

Data Index: 578827 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1339089 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0904. Min Act: -0.0001

Data Index: 759712 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1062542 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0836. Min Act: -0.0001

Data Index: 454715 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1234225 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0770. Min Act: -0.0001

Data Index: 457518 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1108085 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0767. Min Act: -0.0001

Data Index: 260227 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1334047 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0773. Min Act: -0.0001

Data Index: 468340 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0765. Min Act: -0.0001

Data Index: 463576 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1126512 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1179458 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0691. Min Act: -0.0001

Data Index: 240227 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1181815 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0715. Min Act: -0.0001

Data Index: 312867 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0687. Min Act: -0.0001

Data Index: 626086 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0706. Min Act: -0.0001

Data Index: 980523 (C4 (Web Text))

Max Activating Token Index: 35