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

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

Neuron 2782 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.7827. Min Act: -0.0002

Data Index: 497175 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.2940. Min Act: -0.0002

Data Index: 1274334 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1791. Min Act: -0.0002

Data Index: 1114650 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.2293. Min Act: -0.0002

Data Index: 184782 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1381. Min Act: -0.0002

Data Index: 850336 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1585. Min Act: -0.0002

Data Index: 410923 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1211. Min Act: -0.0002

Data Index: 878251 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1808. Min Act: -0.0002

Data Index: 271822 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1126. Min Act: -0.0002

Data Index: 186271 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0546. Min Act: -0.0003

Data Index: 1351337 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0718. Min Act: -0.0002

Data Index: 541534 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0294. Min Act: -0.0002

Data Index: 468142 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.1385. Min Act: -0.0002

Data Index: 1232824 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0054. Min Act: -0.0002

Data Index: 735057 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0349. Min Act: -0.0002

Data Index: 609583 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 2.7827. Min Range: -2.7827

Max Act: 1.9852. Min Act: -0.0002

Data Index: 1012014 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0703. Min Act: -0.0002

Data Index: 197773 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0748. Min Act: -0.0002

Data Index: 66883 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 2.7827. Min Range: -2.7827

Max Act: 2.0404. Min Act: -0.0002

Data Index: 94720 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 2.7827. Min Range: -2.7827

Max Act: 1.9851. Min Act: -0.0002

Data Index: 332959 (C4 (Web Text))

Max Activating Token Index: 665