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

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

Neuron 155 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1450100 (Python Code)

Max Activating Token Index: 757

Text #1

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1470922 (Python Code)

Max Activating Token Index: 980

Text #2

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1439562 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1625289 (Python Code)

Max Activating Token Index: 1010

Text #4

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1613144 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1393649 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1449396 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1513124 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1531946 (Python Code)

Max Activating Token Index: 616

Text #9

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1638401 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1423946 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1382138 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1569977 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1462162 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1441783 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1477501 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1605724 (Python Code)

Max Activating Token Index: 753

Text #17

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1566552 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1435030 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1457635 (Python Code)

Max Activating Token Index: 821