Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3754 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1043. Min Act: -0.0003

Data Index: 873247 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1009. Min Act: -0.0003

Data Index: 1262882 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1043. Min Act: -0.0003

Data Index: 8120 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0957. Min Act: -0.0003

Data Index: 543497 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0961. Min Act: -0.0003

Data Index: 16437 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1012778 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0896. Min Act: -0.0003

Data Index: 1301833 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1304123 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0899. Min Act: -0.0003

Data Index: 668659 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0873. Min Act: -0.0002

Data Index: 464945 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0851. Min Act: -0.0003

Data Index: 127271 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0847. Min Act: -0.0003

Data Index: 1031638 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0800. Min Act: -0.0003

Data Index: 674472 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0833. Min Act: -0.0003

Data Index: 1129913 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0850. Min Act: -0.0003

Data Index: 580024 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0886. Min Act: -0.0003

Data Index: 524738 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0835. Min Act: -0.0003

Data Index: 1100471 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0773. Min Act: -0.0002

Data Index: 976418 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0795. Min Act: -0.0003

Data Index: 1094227 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0775. Min Act: -0.0003

Data Index: 805382 (C4 (Web Text))

Max Activating Token Index: 803