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

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

Neuron 1656 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: 1.1909. Min Range: -1.1909

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1581038 (Python Code)

Max Activating Token Index: 887

Text #1

Max Range: 1.1909. Min Range: -1.1909

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1616391 (Python Code)

Max Activating Token Index: 402

Text #2

Max Range: 1.1909. Min Range: -1.1909

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1569502 (Python Code)

Max Activating Token Index: 311

Text #3

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1528630 (Python Code)

Max Activating Token Index: 173

Text #4

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.9565. Min Act: -0.0000

Data Index: 829757 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.1909. Min Range: -1.1909

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1607405 (Python Code)

Max Activating Token Index: 705

Text #6

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1639369 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.9684. Min Act: -0.0000

Data Index: 579153 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.9255. Min Act: -0.0000

Data Index: 594400 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1564288 (Python Code)

Max Activating Token Index: 938

Text #10

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1417532 (Python Code)

Max Activating Token Index: 599

Text #11

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1653430 (Python Code)

Max Activating Token Index: 766

Text #12

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1531804 (Python Code)

Max Activating Token Index: 106

Text #13

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1643499 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8005. Min Act: -0.0000

Data Index: 596529 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8681. Min Act: -0.0000

Data Index: 398994 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1545810 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1451092 (Python Code)

Max Activating Token Index: 579

Text #18

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1468226 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 1.1909. Min Range: -1.1909

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1441464 (Python Code)

Max Activating Token Index: 677