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

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

Neuron 4689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.8656. Min Act: -0.0001

Data Index: 1456135 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.7800. Min Act: -0.0001

Data Index: 1492791 (Python Code)

Max Activating Token Index: 385

Text #2

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.6995. Min Act: -0.0001

Data Index: 1390606 (Python Code)

Max Activating Token Index: 302

Text #3

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.6442. Min Act: -0.0001

Data Index: 1379965 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.6255. Min Act: -0.0001

Data Index: 1559826 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.6012. Min Act: -0.0001

Data Index: 1563749 (Python Code)

Max Activating Token Index: 812

Text #6

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.4135. Min Act: -0.0001

Data Index: 1480382 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.4939. Min Act: -0.0001

Data Index: 1520937 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.3526. Min Act: -0.0001

Data Index: 1553612 (Python Code)

Max Activating Token Index: 677

Text #9

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.3717. Min Act: -0.0001

Data Index: 1622519 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.2966. Min Act: -0.0001

Data Index: 1365165 (Python Code)

Max Activating Token Index: 983

Text #11

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.2256. Min Act: -0.0001

Data Index: 1440812 (Python Code)

Max Activating Token Index: 760

Text #12

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.3426. Min Act: -0.0001

Data Index: 1470756 (Python Code)

Max Activating Token Index: 707

Text #13

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.0309. Min Act: -0.0001

Data Index: 1605103 (Python Code)

Max Activating Token Index: 814

Text #14

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.1479. Min Act: -0.0001

Data Index: 670266 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.2076. Min Act: -0.0001

Data Index: 1295363 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.2001. Min Act: -0.0001

Data Index: 45903 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.1353. Min Act: -0.0001

Data Index: 683320 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.1701. Min Act: -0.0001

Data Index: 473318 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.8656. Min Range: -1.8656

Max Act: 1.1459. Min Act: -0.0001

Data Index: 1526261 (Python Code)

Max Activating Token Index: 18