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

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

Neuron 5681 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.7913. Min Act: -0.0001

Data Index: 471421 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.8332. Min Act: -0.0001

Data Index: 1249902 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.5815. Min Act: -0.0001

Data Index: 850664 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.8445. Min Act: -0.0001

Data Index: 270272 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.8767. Min Act: -0.0001

Data Index: 1121162 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.5902. Min Act: -0.0001

Data Index: 1305653 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.5385. Min Act: -0.0000

Data Index: 1288253 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.5356. Min Act: -0.0000

Data Index: 1112501 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.8490. Min Act: -0.0001

Data Index: 920656 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.4597. Min Act: -0.0000

Data Index: 745271 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.4763. Min Act: -0.0000

Data Index: 332694 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.4170. Min Act: -0.0001

Data Index: 312952 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.3746. Min Act: -0.0001

Data Index: 1085611 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.1618. Min Act: -0.0000

Data Index: 919919 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.3877. Min Act: -0.0000

Data Index: 301740 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.4822. Min Act: -0.0001

Data Index: 10361 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.3156. Min Act: -0.0001

Data Index: 999024 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1304778 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.2670. Min Act: -0.0001

Data Index: 986050 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.8767. Min Range: -1.8767

Max Act: 1.4686. Min Act: -0.0001

Data Index: 1234482 (C4 (Web Text))

Max Activating Token Index: 993