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

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

Neuron 3582 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0000

Data Index: 46284 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0934. Min Act: -0.0000

Data Index: 928776 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0839. Min Act: -0.0000

Data Index: 369178 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0733. Min Act: -0.0000

Data Index: 988504 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0806. Min Act: -0.0000

Data Index: 688874 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0726. Min Act: -0.0000

Data Index: 755987 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0810. Min Act: -0.0000

Data Index: 540143 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0808. Min Act: -0.0000

Data Index: 283709 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0788. Min Act: -0.0000

Data Index: 374674 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1087804 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0723. Min Act: -0.0000

Data Index: 267276 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0761. Min Act: -0.0000

Data Index: 29463 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0702. Min Act: -0.0000

Data Index: 922263 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0738. Min Act: -0.0000

Data Index: 863103 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0715. Min Act: -0.0000

Data Index: 838411 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0733. Min Act: -0.0000

Data Index: 823672 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0672. Min Act: -0.0000

Data Index: 676456 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1085226 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1357014 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0540. Min Act: -0.0000

Data Index: 85555 (C4 (Web Text))

Max Activating Token Index: 993