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

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

Neuron 3076 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: 1.8306. Min Range: -1.8306

Max Act: 1.8306. Min Act: -0.0002

Data Index: 1035991 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7464. Min Act: -0.0002

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7932. Min Act: -0.0002

Data Index: 1155120 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7943. Min Act: -0.0002

Data Index: 1021207 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7190. Min Act: -0.0002

Data Index: 1221693 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7889. Min Act: -0.0002

Data Index: 1236153 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6908. Min Act: -0.0002

Data Index: 18713 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7385. Min Act: -0.0002

Data Index: 583891 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7354. Min Act: -0.0002

Data Index: 492965 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6781. Min Act: -0.0002

Data Index: 348375 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6937. Min Act: -0.0002

Data Index: 318240 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6442. Min Act: -0.0002

Data Index: 363855 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6480. Min Act: -0.0002

Data Index: 1161010 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7017. Min Act: -0.0002

Data Index: 1306952 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.7143. Min Act: -0.0002

Data Index: 574610 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6269. Min Act: -0.0002

Data Index: 963792 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6866. Min Act: -0.0002

Data Index: 613965 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6719. Min Act: -0.0002

Data Index: 1176292 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.5925. Min Act: -0.0002

Data Index: 171800 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 1.8306. Min Range: -1.8306

Max Act: 1.6450. Min Act: -0.0002

Data Index: 61168 (C4 (Web Text))

Max Activating Token Index: 388