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

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

Neuron 267 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.4314. Min Act: -0.0000

Data Index: 1593009 (Python Code)

Max Activating Token Index: 705

Text #1

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.2638. Min Act: -0.0000

Data Index: 1474006 (Python Code)

Max Activating Token Index: 764

Text #2

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.2086. Min Act: -0.0000

Data Index: 1594466 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.5103. Min Act: -0.0000

Data Index: 1487528 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.3562. Min Act: -0.0000

Data Index: 1604830 (Python Code)

Max Activating Token Index: 876

Text #5

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.5076. Min Act: -0.0000

Data Index: 1458661 (Python Code)

Max Activating Token Index: 989

Text #6

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.2898. Min Act: -0.0000

Data Index: 1602820 (Python Code)

Max Activating Token Index: 966

Text #7

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.4295. Min Act: -0.0000

Data Index: 1491466 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.0886. Min Act: -0.0000

Data Index: 1535480 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.4119. Min Act: -0.0000

Data Index: 1540948 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.2594. Min Act: -0.0000

Data Index: 1362682 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.4050. Min Act: -0.0000

Data Index: 1416784 (Python Code)

Max Activating Token Index: 784

Text #12

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.2184. Min Act: -0.0000

Data Index: 1395422 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.3523. Min Act: -0.0000

Data Index: 1636482 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.2238. Min Act: -0.0000

Data Index: 1384196 (Python Code)

Max Activating Token Index: 929

Text #15

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.6621. Min Act: -0.0000

Data Index: 1578383 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.3323. Min Act: -0.0000

Data Index: 1516015 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.1834. Min Act: -0.0000

Data Index: 1485111 (Python Code)

Max Activating Token Index: 644

Text #18

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.3207. Min Act: -0.0000

Data Index: 1598646 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 3.6621. Min Range: -3.6621

Max Act: 3.4782. Min Act: -0.0000

Data Index: 1589256 (Python Code)

Max Activating Token Index: 264