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

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

Neuron 2343 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: 6.3643. Min Range: -6.3643

Max Act: 6.3643. Min Act: -0.0000

Data Index: 186858 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 6.3643. Min Range: -6.3643

Max Act: 6.1253. Min Act: -0.0000

Data Index: 931383 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.5850. Min Act: -0.0000

Data Index: 1069595 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.7932. Min Act: -0.0000

Data Index: 949839 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.7251. Min Act: -0.0000

Data Index: 93357 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.4891. Min Act: -0.0000

Data Index: 1331975 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.6557. Min Act: -0.0000

Data Index: 331978 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.5715. Min Act: -0.0000

Data Index: 868831 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.4814. Min Act: -0.0000

Data Index: 923462 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.3041. Min Act: -0.0000

Data Index: 45879 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.0726. Min Act: -0.0000

Data Index: 439898 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.9052. Min Act: -0.0000

Data Index: 776137 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.8586. Min Act: -0.0000

Data Index: 1202658 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.7374. Min Act: -0.0000

Data Index: 815397 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.5381. Min Act: -0.0000

Data Index: 178716 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.6441. Min Act: -0.0000

Data Index: 19626 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.2359. Min Act: -0.0000

Data Index: 1264580 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.3372. Min Act: -0.0000

Data Index: 1003206 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.1285. Min Act: -0.0000

Data Index: 578898 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.3041. Min Act: -0.0000

Data Index: 1088706 (C4 (Web Text))

Max Activating Token Index: 739