Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3633 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1290. Min Range: -1.1290

Max Act: 1.1290. Min Act: -0.0001

Data Index: 1396130 (Python Code)

Max Activating Token Index: 241

Text #1

Max Range: 1.1290. Min Range: -1.1290

Max Act: 1.0378. Min Act: -0.0001

Data Index: 1436188 (Python Code)

Max Activating Token Index: 625

Text #2

Max Range: 1.1290. Min Range: -1.1290

Max Act: 1.0767. Min Act: -0.0001

Data Index: 1502702 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.9901. Min Act: -0.0001

Data Index: 1365140 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.9249. Min Act: -0.0001

Data Index: 1611378 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 1.1290. Min Range: -1.1290

Max Act: 1.0144. Min Act: -0.0001

Data Index: 1440927 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 1.1290. Min Range: -1.1290

Max Act: 1.0204. Min Act: -0.0001

Data Index: 1427679 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 1.1290. Min Range: -1.1290

Max Act: 1.0382. Min Act: -0.0001

Data Index: 1458203 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.9726. Min Act: -0.0001

Data Index: 1534891 (Python Code)

Max Activating Token Index: 456

Text #9

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.9410. Min Act: -0.0001

Data Index: 1432768 (Python Code)

Max Activating Token Index: 549

Text #10

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.9340. Min Act: -0.0001

Data Index: 1494541 (Python Code)

Max Activating Token Index: 173

Text #11

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.9839. Min Act: -0.0001

Data Index: 1460268 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.9262. Min Act: -0.0001

Data Index: 1505042 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8758. Min Act: -0.0001

Data Index: 1419965 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8334. Min Act: -0.0001

Data Index: 1427187 (Python Code)

Max Activating Token Index: 796

Text #15

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8890. Min Act: -0.0001

Data Index: 1467605 (Python Code)

Max Activating Token Index: 384

Text #16

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1551859 (Python Code)

Max Activating Token Index: 67

Text #17

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8655. Min Act: -0.0001

Data Index: 1477699 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8827. Min Act: -0.0001

Data Index: 1532763 (Python Code)

Max Activating Token Index: 424

Text #19

Max Range: 1.1290. Min Range: -1.1290

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1589308 (Python Code)

Max Activating Token Index: 765