Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 358 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1440082 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1555980 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4709. Min Act: -0.0001

Data Index: 1646619 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4518. Min Act: -0.0001

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4778. Min Act: -0.0001

Data Index: 766444 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1650778 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4512. Min Act: -0.0001

Data Index: 437126 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4331. Min Act: -0.0001

Data Index: 1520510 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.4076. Min Act: -0.0001

Data Index: 464929 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1440844 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1633174 (Python Code)

Max Activating Token Index: 471

Text #11

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3940. Min Act: -0.0001

Data Index: 1361732 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3424. Min Act: -0.0001

Data Index: 1008134 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3800. Min Act: -0.0001

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1438184 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3801. Min Act: -0.0001

Data Index: 1372183 (Python Code)

Max Activating Token Index: 482

Text #16

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1444519 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1389123 (Python Code)

Max Activating Token Index: 377

Text #18

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3400. Min Act: -0.0001

Data Index: 1429402 (Python Code)

Max Activating Token Index: 746

Text #19

Max Range: 0.5345. Min Range: -0.5345

Max Act: 0.3474. Min Act: -0.0001

Data Index: 945476 (C4 (Web Text))

Max Activating Token Index: 887