Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2847 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.8713. Min Act: -0.0000

Data Index: 1446954 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.9522. Min Act: -0.0000

Data Index: 1397857 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.0547. Min Act: -0.0000

Data Index: 1554753 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.4235. Min Act: -0.0000

Data Index: 1405935 (Python Code)

Max Activating Token Index: 911

Text #4

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.2959. Min Act: -0.0000

Data Index: 1642583 (Python Code)

Max Activating Token Index: 488

Text #5

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.7351. Min Act: -0.0000

Data Index: 1635861 (Python Code)

Max Activating Token Index: 334

Text #6

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.0947. Min Act: -0.0000

Data Index: 1482797 (Python Code)

Max Activating Token Index: 220

Text #7

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.9025. Min Act: -0.0000

Data Index: 1555945 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.0461. Min Act: -0.0000

Data Index: 1393833 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.9175. Min Act: -0.0000

Data Index: 1423781 (Python Code)

Max Activating Token Index: 165

Text #10

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.7015. Min Act: -0.0000

Data Index: 1504756 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.6911. Min Act: -0.0000

Data Index: 1415916 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.4651. Min Act: -0.0000

Data Index: 1430293 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.4257. Min Act: -0.0000

Data Index: 1422234 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.1593. Min Act: -0.0000

Data Index: 1549243 (Python Code)

Max Activating Token Index: 299

Text #15

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.4115. Min Act: -0.0000

Data Index: 1603618 (Python Code)

Max Activating Token Index: 119

Text #16

Max Range: 5.9522. Min Range: -5.9522

Max Act: 5.2940. Min Act: -0.0000

Data Index: 1451769 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.4163. Min Act: -0.0000

Data Index: 1645268 (Python Code)

Max Activating Token Index: 185

Text #18

Max Range: 5.9522. Min Range: -5.9522

Max Act: 4.5587. Min Act: -0.0000

Data Index: 1522288 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 5.9522. Min Range: -5.9522

Max Act: 3.9962. Min Act: -0.0000

Data Index: 1418695 (Python Code)

Max Activating Token Index: 831