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

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

Neuron 1822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1485. Min Range: -5.1485

Max Act: 5.1485. Min Act: -0.0000

Data Index: 587814 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.6560. Min Act: -0.0000

Data Index: 1405332 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.1585. Min Act: -0.0000

Data Index: 1422403 (Python Code)

Max Activating Token Index: 979

Text #3

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.1055. Min Act: -0.0000

Data Index: 636809 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.0168. Min Act: -0.0000

Data Index: 1447466 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.0590. Min Act: -0.0000

Data Index: 1607616 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.0074. Min Act: -0.0000

Data Index: 1393883 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.9894. Min Act: -0.0000

Data Index: 1451393 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.7171. Min Act: -0.0000

Data Index: 1625827 (Python Code)

Max Activating Token Index: 218

Text #9

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.6248. Min Act: -0.0000

Data Index: 904232 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 5.1485. Min Range: -5.1485

Max Act: 2.9061. Min Act: -0.0000

Data Index: 456283 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.3436. Min Act: -0.0000

Data Index: 1575780 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.8307. Min Act: -0.0000

Data Index: 715701 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.5032. Min Act: -0.0000

Data Index: 674956 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.5550. Min Act: -0.0000

Data Index: 820391 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.2335. Min Act: -0.0000

Data Index: 412489 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.4034. Min Act: -0.0000

Data Index: 1373212 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.3949. Min Act: -0.0000

Data Index: 540197 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.4123. Min Act: -0.0000

Data Index: 686051 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 5.1485. Min Range: -5.1485

Max Act: 2.8544. Min Act: -0.0000

Data Index: 225513 (C4 (Web Text))

Max Activating Token Index: 97