Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 175 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1250171 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3787. Min Act: -0.0001

Data Index: 898036 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3949. Min Act: -0.0002

Data Index: 1234740 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.4194. Min Act: -0.0001

Data Index: 188221 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3895. Min Act: -0.0002

Data Index: 1290052 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3697. Min Act: -0.0001

Data Index: 784970 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3089. Min Act: -0.0002

Data Index: 14465 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3261. Min Act: -0.0002

Data Index: 1166904 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3190. Min Act: -0.0001

Data Index: 68656 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2996. Min Act: -0.0001

Data Index: 861031 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2883. Min Act: -0.0002

Data Index: 22099 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3014. Min Act: -0.0001

Data Index: 72209 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1357719 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2658. Min Act: -0.0002

Data Index: 866442 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2829. Min Act: -0.0002

Data Index: 814831 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2729. Min Act: -0.0002

Data Index: 782097 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.3031. Min Act: -0.0001

Data Index: 244798 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2779. Min Act: -0.0002

Data Index: 1337618 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2680. Min Act: -0.0001

Data Index: 203837 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.4294. Min Range: -0.4294

Max Act: 0.2386. Min Act: -0.0002

Data Index: 629194 (C4 (Web Text))

Max Activating Token Index: 67