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

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

Neuron 1015 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1445168 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2156. Min Act: -0.0001

Data Index: 694569 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1411262 (Python Code)

Max Activating Token Index: 295

Text #3

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1499913 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1481014 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1364291 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1539635 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1487873 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1491315 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1623. Min Act: -0.0001

Data Index: 292524 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1539033 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1527808 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1703. Min Act: -0.0001

Data Index: 55696 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1539. Min Act: -0.0001

Data Index: 19724 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1681. Min Act: -0.0001

Data Index: 394166 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1644408 (Python Code)

Max Activating Token Index: 133

Text #16

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1506548 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1459540 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1655096 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1271514 (C4 (Web Text))

Max Activating Token Index: 837