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

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

Neuron 3654 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.7575. Min Act: -0.0001

Data Index: 1426891 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.7314. Min Act: -0.0001

Data Index: 1430558 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.6167. Min Act: -0.0001

Data Index: 1404681 (Python Code)

Max Activating Token Index: 185

Text #3

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4839. Min Act: -0.0001

Data Index: 1576673 (Python Code)

Max Activating Token Index: 269

Text #4

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.3306. Min Act: -0.0001

Data Index: 1634636 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.2391. Min Act: -0.0001

Data Index: 1484564 (Python Code)

Max Activating Token Index: 546

Text #6

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.2077. Min Act: -0.0001

Data Index: 1505089 (Python Code)

Max Activating Token Index: 194

Text #7

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1853. Min Act: -0.0001

Data Index: 1457301 (Python Code)

Max Activating Token Index: 432

Text #8

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.0973. Min Act: -0.0001

Data Index: 1569413 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.0499. Min Act: -0.0001

Data Index: 1500855 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1520. Min Act: -0.0001

Data Index: 1643970 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1043. Min Act: -0.0001

Data Index: 1576458 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1031. Min Act: -0.0001

Data Index: 1472334 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1685. Min Act: -0.0001

Data Index: 1436546 (Python Code)

Max Activating Token Index: 352

Text #14

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.0727. Min Act: -0.0001

Data Index: 1577884 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1243. Min Act: -0.0001

Data Index: 1408834 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1236. Min Act: -0.0001

Data Index: 1531917 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1451. Min Act: -0.0001

Data Index: 1442554 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 1.7575. Min Range: -1.7575

Max Act: 0.9746. Min Act: -0.0001

Data Index: 1516593 (Python Code)

Max Activating Token Index: 589

Text #19

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.1260. Min Act: -0.0001

Data Index: 1650781 (Python Code)

Max Activating Token Index: 973