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

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

Neuron 3387 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2548. Min Act: -0.0001

Data Index: 1549398 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3258. Min Act: -0.0001

Data Index: 1376583 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1395765 (Python Code)

Max Activating Token Index: 515

Text #3

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3036. Min Act: -0.0001

Data Index: 1497212 (Python Code)

Max Activating Token Index: 829

Text #4

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1632639 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3260. Min Act: -0.0001

Data Index: 1494243 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2051. Min Act: -0.0001

Data Index: 1439273 (Python Code)

Max Activating Token Index: 156

Text #7

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.4561. Min Act: -0.0001

Data Index: 1512990 (Python Code)

Max Activating Token Index: 468

Text #8

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1651250 (Python Code)

Max Activating Token Index: 684

Text #9

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1389162 (Python Code)

Max Activating Token Index: 623

Text #10

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3574. Min Act: -0.0001

Data Index: 1645494 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1488. Min Act: -0.0001

Data Index: 1446327 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1256. Min Act: -0.0001

Data Index: 1419664 (Python Code)

Max Activating Token Index: 559

Text #13

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1415. Min Act: -0.0001

Data Index: 1642476 (Python Code)

Max Activating Token Index: 420

Text #14

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1517683 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1151. Min Act: -0.0001

Data Index: 1540108 (Python Code)

Max Activating Token Index: 147

Text #16

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2276. Min Act: -0.0001

Data Index: 1589833 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.0640. Min Act: -0.0001

Data Index: 1433246 (Python Code)

Max Activating Token Index: 397

Text #18

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.0864. Min Act: -0.0001

Data Index: 1414399 (Python Code)

Max Activating Token Index: 411

Text #19

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1107. Min Act: -0.0001

Data Index: 1493828 (Python Code)

Max Activating Token Index: 71