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

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

Neuron 3571 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.9551. Min Act: -0.0000

Data Index: 666578 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1286150 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.8163. Min Act: -0.0000

Data Index: 360821 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7511. Min Act: -0.0000

Data Index: 901204 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7740. Min Act: -0.0000

Data Index: 352211 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7505. Min Act: -0.0000

Data Index: 996000 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6898. Min Act: -0.0000

Data Index: 735807 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6749. Min Act: -0.0000

Data Index: 347430 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7395. Min Act: -0.0000

Data Index: 3643 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1548183 (Python Code)

Max Activating Token Index: 513

Text #10

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1285699 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1016536 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1311593 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.5893. Min Act: -0.0000

Data Index: 760435 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.5787. Min Act: -0.0000

Data Index: 194636 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1564330 (Python Code)

Max Activating Token Index: 921

Text #16

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1097073 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.5901. Min Act: -0.0000

Data Index: 534717 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.5696. Min Act: -0.0000

Data Index: 245183 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.5815. Min Act: -0.0000

Data Index: 518494 (C4 (Web Text))

Max Activating Token Index: 226