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

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

Neuron 2363 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4626. Min Range: -3.4626

Max Act: 3.0985. Min Act: -0.0000

Data Index: 1634368 (Python Code)

Max Activating Token Index: 894

Text #1

Max Range: 3.4626. Min Range: -3.4626

Max Act: 3.4626. Min Act: -0.0000

Data Index: 1515974 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 3.4626. Min Range: -3.4626

Max Act: 3.0283. Min Act: -0.0000

Data Index: 1363775 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.6348. Min Act: -0.0000

Data Index: 1387597 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.7057. Min Act: -0.0000

Data Index: 1436748 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5314. Min Act: -0.0000

Data Index: 1502131 (Python Code)

Max Activating Token Index: 743

Text #6

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5272. Min Act: -0.0000

Data Index: 1407091 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5301. Min Act: -0.0000

Data Index: 1472552 (Python Code)

Max Activating Token Index: 172

Text #8

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.6927. Min Act: -0.0000

Data Index: 1636917 (Python Code)

Max Activating Token Index: 161

Text #9

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5767. Min Act: 0.0001

Data Index: 1594259 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5515. Min Act: -0.0000

Data Index: 1593391 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.3419. Min Act: 0.0000

Data Index: 1475275 (Python Code)

Max Activating Token Index: 139

Text #12

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5602. Min Act: -0.0000

Data Index: 1600686 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.4972. Min Act: -0.0000

Data Index: 1364489 (Python Code)

Max Activating Token Index: 335

Text #14

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5191. Min Act: 0.0000

Data Index: 1459282 (Python Code)

Max Activating Token Index: 658

Text #15

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.4336. Min Act: -0.0000

Data Index: 1639784 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5148. Min Act: 0.0001

Data Index: 1473935 (Python Code)

Max Activating Token Index: 796

Text #17

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.3956. Min Act: -0.0000

Data Index: 1547788 (Python Code)

Max Activating Token Index: 858

Text #18

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.4583. Min Act: -0.0000

Data Index: 1423541 (Python Code)

Max Activating Token Index: 606

Text #19

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.2979. Min Act: 0.0000

Data Index: 1596778 (Python Code)

Max Activating Token Index: 921