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

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

Neuron 3858 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.4325. Min Range: -10.4325

Max Act: 10.4325. Min Act: -0.0000

Data Index: 487213 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 10.4325. Min Range: -10.4325

Max Act: 4.8537. Min Act: -0.0000

Data Index: 793100 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 10.4325. Min Range: -10.4325

Max Act: 4.7631. Min Act: -0.0000

Data Index: 768747 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 10.4325. Min Range: -10.4325

Max Act: 4.4688. Min Act: -0.0000

Data Index: 457644 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 10.4325. Min Range: -10.4325

Max Act: 4.9560. Min Act: -0.0000

Data Index: 1031385 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 10.4325. Min Range: -10.4325

Max Act: 3.6550. Min Act: -0.0000

Data Index: 44873 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 10.4325. Min Range: -10.4325

Max Act: 3.0927. Min Act: -0.0000

Data Index: 1245425 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 10.4325. Min Range: -10.4325

Max Act: 3.3265. Min Act: -0.0000

Data Index: 198691 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 10.4325. Min Range: -10.4325

Max Act: 3.2843. Min Act: -0.0000

Data Index: 1211419 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.4633. Min Act: -0.0000

Data Index: 230510 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 10.4325. Min Range: -10.4325

Max Act: 3.0234. Min Act: -0.0000

Data Index: 934206 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.9778. Min Act: -0.0000

Data Index: 1163430 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.8517. Min Act: -0.0000

Data Index: 125502 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.7956. Min Act: -0.0000

Data Index: 1255088 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.7471. Min Act: -0.0000

Data Index: 1240354 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.4165. Min Act: -0.0000

Data Index: 1056761 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.6262. Min Act: -0.0000

Data Index: 796873 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.0576. Min Act: -0.0000

Data Index: 497540 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.5606. Min Act: -0.0000

Data Index: 745448 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 10.4325. Min Range: -10.4325

Max Act: 2.2735. Min Act: -0.0000

Data Index: 611215 (C4 (Web Text))

Max Activating Token Index: 587