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

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

Neuron 1197 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: 1.0564. Min Range: -1.0564

Max Act: 1.0564. Min Act: -0.0001

Data Index: 30176 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.9818. Min Act: -0.0001

Data Index: 397291 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.8655. Min Act: -0.0001

Data Index: 593869 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.8584. Min Act: -0.0001

Data Index: 343687 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.9044. Min Act: -0.0001

Data Index: 1267419 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1316087 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7705. Min Act: -0.0001

Data Index: 264787 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6895. Min Act: -0.0001

Data Index: 1055582 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7894. Min Act: -0.0001

Data Index: 837604 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7555. Min Act: -0.0001

Data Index: 871563 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7263. Min Act: -0.0001

Data Index: 1291819 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6484. Min Act: -0.0001

Data Index: 292018 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7449. Min Act: -0.0001

Data Index: 1245414 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7178. Min Act: -0.0001

Data Index: 369294 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7109. Min Act: -0.0001

Data Index: 892538 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7364. Min Act: -0.0001

Data Index: 149412 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7354. Min Act: -0.0001

Data Index: 632328 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6447. Min Act: -0.0001

Data Index: 1182728 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.7271. Min Act: -0.0001

Data Index: 7855 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 1.0564. Min Range: -1.0564

Max Act: 0.6725. Min Act: -0.0001

Data Index: 798591 (C4 (Web Text))

Max Activating Token Index: 281