Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1129 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2331. Min Act: -0.0002

Data Index: 7521 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2338. Min Act: -0.0002

Data Index: 45938 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1946. Min Act: -0.0002

Data Index: 640167 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1835. Min Act: -0.0002

Data Index: 584023 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1687. Min Act: -0.0002

Data Index: 819366 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1643. Min Act: -0.0002

Data Index: 774373 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1503. Min Act: -0.0002

Data Index: 625953 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1650. Min Act: -0.0002

Data Index: 656333 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1500. Min Act: -0.0002

Data Index: 224581 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1496. Min Act: -0.0002

Data Index: 1585648 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1562. Min Act: -0.0002

Data Index: 922562 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1393. Min Act: -0.0002

Data Index: 1041272 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1445. Min Act: -0.0002

Data Index: 40398 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1522. Min Act: -0.0002

Data Index: 570187 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1525. Min Act: -0.0002

Data Index: 108287 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1501. Min Act: -0.0002

Data Index: 346612 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1519. Min Act: -0.0002

Data Index: 132281 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1513. Min Act: -0.0002

Data Index: 306854 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1555. Min Act: -0.0002

Data Index: 788196 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1447. Min Act: -0.0002

Data Index: 662844 (C4 (Web Text))

Max Activating Token Index: 184