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

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

Neuron 1470 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: 0.0554. Min Range: -0.0554

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1633299 (Python Code)

Max Activating Token Index: 965

Text #1

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0552. Min Act: -0.0004

Data Index: 250204 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0539. Min Act: -0.0003

Data Index: 241613 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0507. Min Act: -0.0003

Data Index: 184607 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0526. Min Act: -0.0002

Data Index: 692435 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0509. Min Act: -0.0003

Data Index: 221498 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0504. Min Act: 0.0001

Data Index: 1538321 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0512. Min Act: -0.0003

Data Index: 718739 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0499. Min Act: -0.0002

Data Index: 720830 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0492. Min Act: -0.0002

Data Index: 548544 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1387935 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1230659 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0491. Min Act: -0.0003

Data Index: 990145 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0498. Min Act: -0.0003

Data Index: 239500 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1359211 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0471. Min Act: 0.0000

Data Index: 1240924 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0486. Min Act: -0.0002

Data Index: 838499 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0483. Min Act: -0.0003

Data Index: 8517 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0465. Min Act: -0.0004

Data Index: 224391 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0480. Min Act: -0.0001

Data Index: 978272 (C4 (Web Text))

Max Activating Token Index: 683