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

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

Neuron 4874 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: 3.0645. Min Range: -3.0645

Max Act: 3.0645. Min Act: -0.0001

Data Index: 1379105 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 3.0645. Min Range: -3.0645

Max Act: 3.0645. Min Act: -0.0001

Data Index: 1369977 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8989. Min Act: -0.0001

Data Index: 1509754 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8926. Min Act: -0.0001

Data Index: 1450106 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.7622. Min Act: -0.0001

Data Index: 1499762 (Python Code)

Max Activating Token Index: 19

Text #5

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.8650. Min Act: -0.0001

Data Index: 1506297 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.7645. Min Act: -0.0001

Data Index: 1605503 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.7645. Min Act: -0.0001

Data Index: 1644790 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.5043. Min Act: -0.0001

Data Index: 1641331 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.3557. Min Act: -0.0001

Data Index: 1656658 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.4436. Min Act: -0.0001

Data Index: 1454139 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.4436. Min Act: -0.0001

Data Index: 1522579 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.3892. Min Act: -0.0001

Data Index: 1644557 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.3210. Min Act: -0.0001

Data Index: 1597865 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.3210. Min Act: -0.0001

Data Index: 1520253 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.3378. Min Act: -0.0001

Data Index: 1362313 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.2006. Min Act: -0.0001

Data Index: 1438772 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.0795. Min Act: -0.0001

Data Index: 1535522 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.4263. Min Act: -0.0001

Data Index: 1542433 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 3.0645. Min Range: -3.0645

Max Act: 2.3002. Min Act: -0.0001

Data Index: 1371172 (Python Code)

Max Activating Token Index: 11