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

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

Neuron 2186 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1333270 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.8390. Min Act: -0.0001

Data Index: 695067 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.8108. Min Act: -0.0000

Data Index: 559940 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6216. Min Act: -0.0001

Data Index: 992760 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1293310 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5999. Min Act: -0.0000

Data Index: 89072 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6146. Min Act: 0.0000

Data Index: 71784 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6058. Min Act: -0.0001

Data Index: 227786 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6234. Min Act: -0.0000

Data Index: 864380 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6151. Min Act: -0.0000

Data Index: 575006 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6022. Min Act: -0.0001

Data Index: 933327 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6130. Min Act: -0.0000

Data Index: 308119 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5858. Min Act: -0.0000

Data Index: 82221 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5559. Min Act: -0.0000

Data Index: 843828 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5702. Min Act: -0.0000

Data Index: 958084 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5435. Min Act: -0.0000

Data Index: 919309 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5829. Min Act: -0.0000

Data Index: 212384 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5399. Min Act: -0.0000

Data Index: 410619 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5539. Min Act: -0.0000

Data Index: 665266 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5317. Min Act: -0.0001

Data Index: 987497 (C4 (Web Text))

Max Activating Token Index: 937