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

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

Neuron 1861 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.1094. Min Act: -0.0001

Data Index: 883838 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.1013. Min Act: -0.0000

Data Index: 654822 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0940. Min Act: -0.0000

Data Index: 137730 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0776. Min Act: -0.0001

Data Index: 406532 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0711. Min Act: -0.0000

Data Index: 837774 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0735. Min Act: -0.0000

Data Index: 567476 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0776. Min Act: -0.0000

Data Index: 439073 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0758. Min Act: -0.0001

Data Index: 916910 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0707. Min Act: -0.0000

Data Index: 57433 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0727. Min Act: -0.0000

Data Index: 919424 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0749. Min Act: -0.0001

Data Index: 981544 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0647. Min Act: -0.0001

Data Index: 458069 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0715. Min Act: -0.0000

Data Index: 413228 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1350172 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0725. Min Act: -0.0001

Data Index: 921006 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0640. Min Act: -0.0000

Data Index: 713204 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0645. Min Act: -0.0000

Data Index: 209310 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0656. Min Act: -0.0001

Data Index: 716856 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1233630 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0659. Min Act: -0.0001

Data Index: 318185 (C4 (Web Text))

Max Activating Token Index: 997