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

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

Neuron 5836 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.8821. Min Act: -0.0003

Data Index: 1029308 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.9187. Min Act: -0.0002

Data Index: 134418 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.8485. Min Act: -0.0002

Data Index: 384402 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.7657. Min Act: -0.0002

Data Index: 1343924 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.8097. Min Act: -0.0002

Data Index: 1077377 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.7638. Min Act: -0.0002

Data Index: 1292421 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.7058. Min Act: -0.0002

Data Index: 859434 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.6441. Min Act: -0.0002

Data Index: 369048 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.7051. Min Act: -0.0002

Data Index: 404765 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.6499. Min Act: -0.0002

Data Index: 1108993 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.6511. Min Act: -0.0002

Data Index: 1345003 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.6131. Min Act: -0.0002

Data Index: 43736 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.6261. Min Act: -0.0002

Data Index: 1281926 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.6023. Min Act: -0.0002

Data Index: 1262362 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.5811. Min Act: -0.0002

Data Index: 1300401 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.6550. Min Act: -0.0002

Data Index: 659119 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.5614. Min Act: -0.0002

Data Index: 249790 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.5977. Min Act: -0.0002

Data Index: 1165384 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.5701. Min Act: -0.0002

Data Index: 35069 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.9187. Min Range: -1.9187

Max Act: 1.5484. Min Act: -0.0002

Data Index: 27621 (C4 (Web Text))

Max Activating Token Index: 889