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

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

Neuron 3487 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.6185. Min Act: -0.0001

Data Index: 1656300 (Python Code)

Max Activating Token Index: 552

Text #1

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.6286. Min Act: -0.0001

Data Index: 1421486 (Python Code)

Max Activating Token Index: 454

Text #2

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5710. Min Act: -0.0001

Data Index: 1382405 (Python Code)

Max Activating Token Index: 391

Text #3

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1645287 (Python Code)

Max Activating Token Index: 476

Text #4

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5484. Min Act: -0.0001

Data Index: 1550075 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1489996 (Python Code)

Max Activating Token Index: 289

Text #6

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5359. Min Act: -0.0001

Data Index: 1452274 (Python Code)

Max Activating Token Index: 295

Text #7

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1616770 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4958. Min Act: -0.0001

Data Index: 1404321 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5260. Min Act: -0.0001

Data Index: 1481225 (Python Code)

Max Activating Token Index: 228

Text #10

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5186. Min Act: -0.0001

Data Index: 1406087 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5234. Min Act: -0.0001

Data Index: 1424883 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4630. Min Act: -0.0001

Data Index: 1612532 (Python Code)

Max Activating Token Index: 669

Text #13

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5206. Min Act: -0.0001

Data Index: 1423433 (Python Code)

Max Activating Token Index: 680

Text #14

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5546. Min Act: -0.0001

Data Index: 1447781 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5011. Min Act: -0.0001

Data Index: 1487312 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5700. Min Act: -0.0001

Data Index: 1424904 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5235. Min Act: -0.0001

Data Index: 1399540 (Python Code)

Max Activating Token Index: 358

Text #18

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4837. Min Act: -0.0001

Data Index: 1366493 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5208. Min Act: -0.0001

Data Index: 1426955 (Python Code)

Max Activating Token Index: 762