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

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

Neuron 668 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4621. Min Range: -3.4621

Max Act: 3.3803. Min Act: -0.0000

Data Index: 705180 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 3.4621. Min Range: -3.4621

Max Act: 3.4621. Min Act: -0.0000

Data Index: 710606 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 3.4621. Min Range: -3.4621

Max Act: 3.0243. Min Act: -0.0000

Data Index: 450879 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.8824. Min Act: -0.0000

Data Index: 583852 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 3.4621. Min Range: -3.4621

Max Act: 3.0385. Min Act: -0.0000

Data Index: 1009792 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.7335. Min Act: -0.0000

Data Index: 760612 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.4162. Min Act: -0.0000

Data Index: 478052 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.5474. Min Act: -0.0000

Data Index: 394488 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.6788. Min Act: -0.0000

Data Index: 547758 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.6437. Min Act: -0.0000

Data Index: 1223794 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.5271. Min Act: -0.0000

Data Index: 26059 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.4608. Min Act: -0.0000

Data Index: 700585 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.3329. Min Act: -0.0000

Data Index: 949460 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.4058. Min Act: -0.0000

Data Index: 534983 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.2224. Min Act: -0.0000

Data Index: 467332 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.3269. Min Act: -0.0000

Data Index: 504594 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.2000. Min Act: -0.0000

Data Index: 1045016 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.4230. Min Act: -0.0000

Data Index: 691471 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.2899. Min Act: -0.0000

Data Index: 1209671 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 3.4621. Min Range: -3.4621

Max Act: 2.2666. Min Act: -0.0000

Data Index: 195551 (C4 (Web Text))

Max Activating Token Index: 791