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

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

Neuron 2826 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2585. Min Range: -1.2585

Max Act: 1.1639. Min Act: -0.0001

Data Index: 205460 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 1.2585. Min Range: -1.2585

Max Act: 1.2585. Min Act: -0.0001

Data Index: 1107869 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.2585. Min Range: -1.2585

Max Act: 1.1560. Min Act: -0.0001

Data Index: 740573 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.2585. Min Range: -1.2585

Max Act: 1.1105. Min Act: -0.0001

Data Index: 1037047 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.9275. Min Act: -0.0001

Data Index: 1117573 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.2585. Min Range: -1.2585

Max Act: 1.0898. Min Act: -0.0001

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.6757. Min Act: -0.0001

Data Index: 568996 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.8590. Min Act: -0.0001

Data Index: 478192 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.8540. Min Act: -0.0001

Data Index: 6653 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.9665. Min Act: -0.0001

Data Index: 465161 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.9148. Min Act: -0.0001

Data Index: 387235 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.8090. Min Act: -0.0001

Data Index: 175025 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.9269. Min Act: -0.0001

Data Index: 503653 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.8883. Min Act: -0.0001

Data Index: 546708 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.8917. Min Act: -0.0001

Data Index: 54150 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.9480. Min Act: -0.0001

Data Index: 388032 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1345588 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.7889. Min Act: -0.0001

Data Index: 1063991 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.9487. Min Act: -0.0001

Data Index: 146921 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 1.2585. Min Range: -1.2585

Max Act: 0.9459. Min Act: -0.0001

Data Index: 747522 (C4 (Web Text))

Max Activating Token Index: 859