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

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

Neuron 6139 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: 3.3183. Min Range: -3.3183

Max Act: 3.3183. Min Act: -0.0001

Data Index: 1606523 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 3.3183. Min Range: -3.3183

Max Act: 3.0229. Min Act: -0.0001

Data Index: 1412101 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.8368. Min Act: -0.0001

Data Index: 1434598 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.8843. Min Act: -0.0001

Data Index: 1382290 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.8066. Min Act: -0.0001

Data Index: 1438241 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.7636. Min Act: -0.0001

Data Index: 1399768 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.6500. Min Act: -0.0001

Data Index: 1373989 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.6345. Min Act: -0.0001

Data Index: 1525786 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.4935. Min Act: -0.0001

Data Index: 1360550 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.6116. Min Act: -0.0001

Data Index: 1505419 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.5262. Min Act: -0.0001

Data Index: 1373171 (Python Code)

Max Activating Token Index: 422

Text #11

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.5201. Min Act: -0.0001

Data Index: 1471719 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.6102. Min Act: -0.0001

Data Index: 1490219 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.4557. Min Act: -0.0001

Data Index: 1546697 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.3584. Min Act: -0.0001

Data Index: 1463708 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.5646. Min Act: -0.0001

Data Index: 1362352 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.2726. Min Act: -0.0001

Data Index: 1623206 (Python Code)

Max Activating Token Index: 765

Text #17

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.3754. Min Act: -0.0001

Data Index: 1359857 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.3377. Min Act: -0.0001

Data Index: 1584245 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 3.3183. Min Range: -3.3183

Max Act: 2.3304. Min Act: -0.0001

Data Index: 1643699 (Python Code)

Max Activating Token Index: 811