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

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

Neuron 5439 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: 0.8098. Min Range: -0.8098

Max Act: 0.8098. Min Act: -0.0000

Data Index: 76136 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.7598. Min Act: -0.0000

Data Index: 468476 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.7903. Min Act: -0.0000

Data Index: 404135 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.6777. Min Act: -0.0000

Data Index: 679056 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1118108 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1551788 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5451. Min Act: -0.0000

Data Index: 574375 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5933. Min Act: -0.0000

Data Index: 642359 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1652980 (Python Code)

Max Activating Token Index: 871

Text #9

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1367301 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1529221 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5619. Min Act: 0.0000

Data Index: 1575597 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1551693 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5168. Min Act: -0.0000

Data Index: 697351 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1645839 (Python Code)

Max Activating Token Index: 653

Text #15

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1410085 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1590370 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5261. Min Act: -0.0000

Data Index: 914656 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1486573 (Python Code)

Max Activating Token Index: 720

Text #19

Max Range: 0.8098. Min Range: -0.8098

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1478522 (Python Code)

Max Activating Token Index: 543