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

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

Neuron 534 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8996. Min Range: -3.8996

Max Act: 3.8996. Min Act: -0.0000

Data Index: 1429166 (Python Code)

Max Activating Token Index: 668

Text #1

Max Range: 3.8996. Min Range: -3.8996

Max Act: 3.2683. Min Act: -0.0000

Data Index: 1636395 (Python Code)

Max Activating Token Index: 169

Text #2

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.8280. Min Act: -0.0000

Data Index: 1610275 (Python Code)

Max Activating Token Index: 623

Text #3

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.8054. Min Act: -0.0000

Data Index: 1339367 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.7033. Min Act: -0.0000

Data Index: 1389135 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.5607. Min Act: -0.0000

Data Index: 1585683 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.8212. Min Act: -0.0000

Data Index: 1610762 (Python Code)

Max Activating Token Index: 557

Text #7

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.4347. Min Act: -0.0000

Data Index: 980107 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.4503. Min Act: -0.0000

Data Index: 1447940 (Python Code)

Max Activating Token Index: 939

Text #9

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.4416. Min Act: -0.0000

Data Index: 1634027 (Python Code)

Max Activating Token Index: 224

Text #10

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.3727. Min Act: -0.0000

Data Index: 1580431 (Python Code)

Max Activating Token Index: 1013

Text #11

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.0912. Min Act: -0.0000

Data Index: 1517528 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.3988. Min Act: -0.0000

Data Index: 1518489 (Python Code)

Max Activating Token Index: 789

Text #13

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.1465. Min Act: 0.0000

Data Index: 1489586 (Python Code)

Max Activating Token Index: 416

Text #14

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.0138. Min Act: -0.0000

Data Index: 1598450 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.1793. Min Act: -0.0000

Data Index: 1453635 (Python Code)

Max Activating Token Index: 461

Text #16

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.1578. Min Act: -0.0000

Data Index: 1087040 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.2428. Min Act: -0.0000

Data Index: 1523555 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.2363. Min Act: 0.0000

Data Index: 1414322 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 3.8996. Min Range: -3.8996

Max Act: 2.1268. Min Act: 0.0000

Data Index: 1631091 (Python Code)

Max Activating Token Index: 821