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

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

Neuron 1188 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: 0.6218. Min Range: -0.6218

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1588079 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5758. Min Act: -0.0001

Data Index: 1494330 (Python Code)

Max Activating Token Index: 493

Text #2

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6218. Min Act: -0.0001

Data Index: 1391433 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5823. Min Act: -0.0001

Data Index: 1609376 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5695. Min Act: -0.0001

Data Index: 1655263 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6108. Min Act: -0.0001

Data Index: 1517885 (Python Code)

Max Activating Token Index: 682

Text #6

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5153. Min Act: -0.0001

Data Index: 1520519 (Python Code)

Max Activating Token Index: 781

Text #7

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5705. Min Act: -0.0001

Data Index: 1626293 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5600. Min Act: -0.0001

Data Index: 1538424 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5780. Min Act: -0.0001

Data Index: 1610421 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5261. Min Act: -0.0001

Data Index: 1396704 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5179. Min Act: -0.0001

Data Index: 1374506 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5036. Min Act: -0.0001

Data Index: 1512962 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5292. Min Act: -0.0001

Data Index: 1628812 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4930. Min Act: -0.0001

Data Index: 1639733 (Python Code)

Max Activating Token Index: 473

Text #15

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5015. Min Act: -0.0001

Data Index: 1636221 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4975. Min Act: -0.0001

Data Index: 1423921 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4987. Min Act: -0.0001

Data Index: 1430511 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4826. Min Act: -0.0001

Data Index: 1370668 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1378857 (Python Code)

Max Activating Token Index: 33