Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5118 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.5381. Min Act: -0.0001

Data Index: 1452987 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1413. Min Act: -0.0001

Data Index: 1401615 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.4407. Min Act: -0.0001

Data Index: 1565818 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.3203. Min Act: -0.0001

Data Index: 1385900 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.3662. Min Act: -0.0001

Data Index: 1465513 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2878. Min Act: -0.0001

Data Index: 1528270 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2422. Min Act: -0.0001

Data Index: 1625006 (Python Code)

Max Activating Token Index: 218

Text #7

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.5152. Min Act: -0.0001

Data Index: 1558825 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.4008. Min Act: -0.0001

Data Index: 1428922 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1304. Min Act: -0.0001

Data Index: 1621124 (Python Code)

Max Activating Token Index: 812

Text #10

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0851. Min Act: -0.0001

Data Index: 1569770 (Python Code)

Max Activating Token Index: 774

Text #11

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1396. Min Act: -0.0001

Data Index: 1545826 (Python Code)

Max Activating Token Index: 336

Text #12

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.3465. Min Act: -0.0001

Data Index: 1610116 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.3918. Min Act: -0.0001

Data Index: 1632997 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1348. Min Act: -0.0001

Data Index: 1433228 (Python Code)

Max Activating Token Index: 397

Text #15

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1400. Min Act: -0.0001

Data Index: 1572462 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1686. Min Act: -0.0001

Data Index: 1384542 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2432. Min Act: -0.0001

Data Index: 1561920 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.2549. Min Act: -0.0001

Data Index: 1619924 (Python Code)

Max Activating Token Index: 971

Text #19

Max Range: 1.5381. Min Range: -1.5381

Max Act: 0.8521. Min Act: -0.0001

Data Index: 1427284 (Python Code)

Max Activating Token Index: 217