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

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

Neuron 3725 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: 5.0570. Min Range: -5.0570

Max Act: 5.0570. Min Act: -0.0000

Data Index: 791170 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.5066. Min Act: -0.0000

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.3758. Min Act: -0.0000

Data Index: 168622 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.6961. Min Act: -0.0000

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.6340. Min Act: -0.0000

Data Index: 633416 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.8298. Min Act: -0.0000

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.2322. Min Act: -0.0001

Data Index: 198343 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.2025. Min Act: -0.0000

Data Index: 91866 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.1172. Min Act: -0.0000

Data Index: 4158 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.0616. Min Act: -0.0000

Data Index: 682959 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 5.0570. Min Range: -5.0570

Max Act: 4.1684. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.8885. Min Act: -0.0000

Data Index: 614014 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.8997. Min Act: -0.0000

Data Index: 391728 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.8815. Min Act: -0.0000

Data Index: 464929 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.7834. Min Act: -0.0000

Data Index: 1269335 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.7737. Min Act: -0.0000

Data Index: 777178 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.6413. Min Act: -0.0000

Data Index: 921632 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.6293. Min Act: -0.0000

Data Index: 42771 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.5808. Min Act: -0.0000

Data Index: 292255 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 5.0570. Min Range: -5.0570

Max Act: 3.5383. Min Act: -0.0000

Data Index: 712788 (C4 (Web Text))

Max Activating Token Index: 27