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

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

Neuron 3476 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: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0003

Data Index: 771398 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0606. Min Act: -0.0003

Data Index: 518208 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0572. Min Act: -0.0003

Data Index: 432877 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0605. Min Act: -0.0003

Data Index: 809952 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0545. Min Act: -0.0003

Data Index: 331548 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1111760 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1172274 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1336375 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1011679 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1245306 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0487. Min Act: -0.0003

Data Index: 790729 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0449. Min Act: -0.0003

Data Index: 397032 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0469. Min Act: -0.0003

Data Index: 622371 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0442. Min Act: -0.0003

Data Index: 548951 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1231107 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1286637 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1106722 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1012017 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0433. Min Act: -0.0003

Data Index: 594728 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1240889 (C4 (Web Text))

Max Activating Token Index: 247