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

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

Neuron 5018 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.5338. Min Act: -0.0001

Data Index: 1513872 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1868. Min Act: -0.0001

Data Index: 1612293 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1629567 (Python Code)

Max Activating Token Index: 914

Text #3

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0228. Min Act: -0.0001

Data Index: 1409161 (Python Code)

Max Activating Token Index: 828

Text #4

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1297348 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.9067. Min Act: -0.0001

Data Index: 1378862 (Python Code)

Max Activating Token Index: 919

Text #6

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.7011. Min Act: -0.0001

Data Index: 1486508 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.9255. Min Act: -0.0001

Data Index: 1627034 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.9233. Min Act: -0.0001

Data Index: 1593977 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.9129. Min Act: -0.0001

Data Index: 1560109 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.8843. Min Act: -0.0001

Data Index: 1474488 (Python Code)

Max Activating Token Index: 853

Text #11

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.9145. Min Act: -0.0001

Data Index: 1594589 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.8368. Min Act: -0.0001

Data Index: 1379174 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.8347. Min Act: -0.0001

Data Index: 1368813 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.8412. Min Act: -0.0001

Data Index: 1405503 (Python Code)

Max Activating Token Index: 269

Text #15

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.8662. Min Act: -0.0001

Data Index: 1560025 (Python Code)

Max Activating Token Index: 752

Text #16

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.8025. Min Act: -0.0001

Data Index: 1367980 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.8471. Min Act: -0.0001

Data Index: 1562605 (Python Code)

Max Activating Token Index: 809

Text #18

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.9443. Min Act: -0.0001

Data Index: 1451422 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.7726. Min Act: -0.0001

Data Index: 1446262 (Python Code)

Max Activating Token Index: 832