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

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

Neuron 1239 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: 1.2176. Min Range: -1.2176

Max Act: 1.2176. Min Act: -0.0002

Data Index: 1331797 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.1125. Min Act: -0.0002

Data Index: 663207 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0877. Min Act: -0.0002

Data Index: 406844 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0706. Min Act: -0.0002

Data Index: 796951 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0669. Min Act: -0.0002

Data Index: 454386 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0469. Min Act: -0.0002

Data Index: 1065736 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0351. Min Act: -0.0003

Data Index: 1041303 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0503. Min Act: -0.0003

Data Index: 261403 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0328. Min Act: -0.0002

Data Index: 1346400 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0324. Min Act: -0.0002

Data Index: 520152 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0352. Min Act: -0.0002

Data Index: 1320219 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0496. Min Act: -0.0002

Data Index: 754961 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0183. Min Act: -0.0002

Data Index: 764873 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0051. Min Act: -0.0002

Data Index: 1236789 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9945. Min Act: -0.0003

Data Index: 220149 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9807. Min Act: -0.0002

Data Index: 1515277 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0078. Min Act: -0.0002

Data Index: 35456 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9970. Min Act: -0.0002

Data Index: 388280 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9916. Min Act: -0.0002

Data Index: 838941 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9701. Min Act: -0.0002

Data Index: 434967 (C4 (Web Text))

Max Activating Token Index: 52