Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1986 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0002

Data Index: 356519 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0586. Min Act: -0.0003

Data Index: 93415 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0565. Min Act: -0.0002

Data Index: 650564 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0562. Min Act: -0.0003

Data Index: 819346 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1017935 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0504. Min Act: -0.0003

Data Index: 605928 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0500. Min Act: -0.0003

Data Index: 37124 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0501. Min Act: -0.0003

Data Index: 357111 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0498. Min Act: -0.0003

Data Index: 272683 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1178304 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0488. Min Act: -0.0002

Data Index: 779226 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0491. Min Act: -0.0002

Data Index: 363298 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1120739 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0470. Min Act: -0.0003

Data Index: 341878 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0468. Min Act: -0.0003

Data Index: 499972 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1299009 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1136336 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1206533 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0454. Min Act: -0.0002

Data Index: 139567 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0455. Min Act: -0.0002

Data Index: 309656 (C4 (Web Text))

Max Activating Token Index: 277