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

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

Neuron 4067 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.1524. Min Act: -0.0001

Data Index: 1369994 (Python Code)

Max Activating Token Index: 832

Text #1

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.1497. Min Act: -0.0001

Data Index: 1519057 (Python Code)

Max Activating Token Index: 126

Text #2

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.1268. Min Act: -0.0001

Data Index: 1598906 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.1009. Min Act: -0.0001

Data Index: 1410562 (Python Code)

Max Activating Token Index: 595

Text #4

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.0094. Min Act: -0.0001

Data Index: 1459869 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.0266. Min Act: -0.0001

Data Index: 1523542 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9562. Min Act: -0.0001

Data Index: 1629302 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9815. Min Act: -0.0001

Data Index: 1571094 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9806. Min Act: -0.0001

Data Index: 1399640 (Python Code)

Max Activating Token Index: 801

Text #9

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9469. Min Act: -0.0001

Data Index: 1500018 (Python Code)

Max Activating Token Index: 691

Text #10

Max Range: 1.1524. Min Range: -1.1524

Max Act: 1.0025. Min Act: -0.0001

Data Index: 1480318 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9386. Min Act: -0.0001

Data Index: 1588341 (Python Code)

Max Activating Token Index: 1004

Text #12

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9304. Min Act: -0.0001

Data Index: 1439013 (Python Code)

Max Activating Token Index: 891

Text #13

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9267. Min Act: -0.0001

Data Index: 1564031 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9319. Min Act: -0.0001

Data Index: 1609193 (Python Code)

Max Activating Token Index: 396

Text #15

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1378259 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9373. Min Act: -0.0001

Data Index: 1532716 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9007. Min Act: -0.0001

Data Index: 1624745 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.9005. Min Act: -0.0001

Data Index: 1577215 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 1.1524. Min Range: -1.1524

Max Act: 0.8755. Min Act: -0.0001

Data Index: 1573241 (Python Code)

Max Activating Token Index: 576