Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0707. Min Act: -0.0003

Data Index: 512084 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0585. Min Act: -0.0003

Data Index: 574653 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0567. Min Act: -0.0003

Data Index: 89925 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0587. Min Act: -0.0003

Data Index: 326640 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0537. Min Act: -0.0003

Data Index: 139982 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0567. Min Act: -0.0003

Data Index: 224429 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0543. Min Act: -0.0003

Data Index: 630797 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0565. Min Act: -0.0003

Data Index: 364896 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1340914 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0530. Min Act: -0.0003

Data Index: 923546 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1135527 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0529. Min Act: -0.0003

Data Index: 722 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1063335 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0544. Min Act: -0.0003

Data Index: 838771 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1191129 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1140571 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0524. Min Act: -0.0003

Data Index: 463220 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0551. Min Act: -0.0003

Data Index: 835879 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0554. Min Act: -0.0003

Data Index: 928800 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1131323 (C4 (Web Text))

Max Activating Token Index: 271