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

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

Neuron 1400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.7204. Min Act: -0.0000

Data Index: 1546841 (Python Code)

Max Activating Token Index: 615

Text #1

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.6528. Min Act: -0.0000

Data Index: 1388068 (Python Code)

Max Activating Token Index: 987

Text #2

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.5148. Min Act: -0.0000

Data Index: 1522276 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.4743. Min Act: -0.0000

Data Index: 1610634 (Python Code)

Max Activating Token Index: 478

Text #4

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.2278. Min Act: -0.0000

Data Index: 1609669 (Python Code)

Max Activating Token Index: 755

Text #5

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.2980. Min Act: -0.0000

Data Index: 1390398 (Python Code)

Max Activating Token Index: 771

Text #6

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.4291. Min Act: -0.0001

Data Index: 1481315 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.2829. Min Act: -0.0000

Data Index: 1469052 (Python Code)

Max Activating Token Index: 536

Text #8

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.1376. Min Act: -0.0000

Data Index: 1649151 (Python Code)

Max Activating Token Index: 946

Text #9

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.3771. Min Act: -0.0000

Data Index: 1632543 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.2404. Min Act: -0.0000

Data Index: 1381099 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.3329. Min Act: -0.0001

Data Index: 1565074 (Python Code)

Max Activating Token Index: 809

Text #12

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.0832. Min Act: -0.0000

Data Index: 1564891 (Python Code)

Max Activating Token Index: 943

Text #13

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.4458. Min Act: -0.0001

Data Index: 1577439 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 2.7204. Min Range: -2.7204

Max Act: 1.8235. Min Act: -0.0000

Data Index: 1573128 (Python Code)

Max Activating Token Index: 169

Text #15

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.1363. Min Act: -0.0000

Data Index: 1552631 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.2564. Min Act: -0.0001

Data Index: 1633049 (Python Code)

Max Activating Token Index: 956

Text #17

Max Range: 2.7204. Min Range: -2.7204

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1617743 (Python Code)

Max Activating Token Index: 309

Text #18

Max Range: 2.7204. Min Range: -2.7204

Max Act: 1.8588. Min Act: -0.0000

Data Index: 1596408 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 2.7204. Min Range: -2.7204

Max Act: 2.1775. Min Act: -0.0000

Data Index: 1415956 (Python Code)

Max Activating Token Index: 860