Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1581 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6218. Min Act: -0.0001

Data Index: 1083405 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5925. Min Act: -0.0001

Data Index: 378655 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5403. Min Act: -0.0001

Data Index: 937769 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5459. Min Act: -0.0001

Data Index: 1474091 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5142. Min Act: -0.0001

Data Index: 102993 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5428. Min Act: -0.0001

Data Index: 1225249 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5373. Min Act: -0.0001

Data Index: 124496 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4867. Min Act: -0.0001

Data Index: 562230 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4904. Min Act: -0.0001

Data Index: 168547 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5111. Min Act: -0.0001

Data Index: 209041 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4810. Min Act: -0.0001

Data Index: 248729 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4850. Min Act: -0.0001

Data Index: 314606 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4799. Min Act: -0.0001

Data Index: 1461709 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4851. Min Act: -0.0001

Data Index: 806471 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5015. Min Act: -0.0001

Data Index: 196128 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4691. Min Act: -0.0001

Data Index: 404669 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4670. Min Act: -0.0001

Data Index: 1289319 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4621. Min Act: -0.0001

Data Index: 1005198 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4876. Min Act: -0.0001

Data Index: 1348203 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4898. Min Act: -0.0001

Data Index: 1441385 (Python Code)

Max Activating Token Index: 899