Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4640. Min Range: -2.4640

Max Act: 2.4640. Min Act: -0.0000

Data Index: 1618060 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.6215. Min Act: -0.0000

Data Index: 1362407 (Python Code)

Max Activating Token Index: 283

Text #2

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.8054. Min Act: -0.0000

Data Index: 1387704 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.6636. Min Act: -0.0000

Data Index: 1374183 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.7245. Min Act: -0.0000

Data Index: 1548956 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1457329 (Python Code)

Max Activating Token Index: 347

Text #6

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.5760. Min Act: -0.0000

Data Index: 1634167 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1415097 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1547029 (Python Code)

Max Activating Token Index: 324

Text #9

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.3492. Min Act: -0.0000

Data Index: 1443402 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1484522 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.3116. Min Act: -0.0000

Data Index: 1392216 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1599992 (Python Code)

Max Activating Token Index: 894

Text #13

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1644751 (Python Code)

Max Activating Token Index: 875

Text #14

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1630655 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1561756 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1379637 (Python Code)

Max Activating Token Index: 734

Text #17

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.2193. Min Act: -0.0000

Data Index: 1426532 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1602958 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 2.4640. Min Range: -2.4640

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1586207 (Python Code)

Max Activating Token Index: 993