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

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

Neuron 3085 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0191. Min Range: -3.0191

Max Act: 3.0191. Min Act: -0.0000

Data Index: 307780 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.7014. Min Act: -0.0000

Data Index: 605920 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.5625. Min Act: -0.0000

Data Index: 491541 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.5347. Min Act: -0.0000

Data Index: 557435 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.4917. Min Act: -0.0000

Data Index: 859847 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.5014. Min Act: -0.0000

Data Index: 1297874 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.5871. Min Act: -0.0000

Data Index: 318576 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.4316. Min Act: -0.0000

Data Index: 504208 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.4870. Min Act: -0.0000

Data Index: 165058 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.4066. Min Act: -0.0000

Data Index: 746268 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3694. Min Act: -0.0000

Data Index: 556045 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3701. Min Act: -0.0000

Data Index: 1176383 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3525. Min Act: -0.0000

Data Index: 1118444 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3523. Min Act: -0.0000

Data Index: 1158202 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3582. Min Act: -0.0000

Data Index: 825481 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3255. Min Act: -0.0000

Data Index: 558528 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3308. Min Act: -0.0000

Data Index: 337450 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3014. Min Act: -0.0000

Data Index: 159091 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.3125. Min Act: -0.0000

Data Index: 468606 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 3.0191. Min Range: -3.0191

Max Act: 2.2803. Min Act: -0.0000

Data Index: 363275 (C4 (Web Text))

Max Activating Token Index: 376