Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0005

Data Index: 1430676 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0396. Min Act: -0.0005

Data Index: 1584071 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0360. Min Act: -0.0005

Data Index: 1601343 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0359. Min Act: -0.0005

Data Index: 1570058 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1430477 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0347. Min Act: -0.0005

Data Index: 1535923 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0369. Min Act: -0.0005

Data Index: 1476432 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0346. Min Act: -0.0005

Data Index: 1403084 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0335. Min Act: -0.0005

Data Index: 1530389 (Python Code)

Max Activating Token Index: 957

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0340. Min Act: -0.0005

Data Index: 1590965 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0330. Min Act: -0.0005

Data Index: 1615072 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0314. Min Act: -0.0005

Data Index: 1487203 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0326. Min Act: -0.0005

Data Index: 1506877 (Python Code)

Max Activating Token Index: 484

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0310. Min Act: -0.0005

Data Index: 1455851 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0316. Min Act: -0.0005

Data Index: 1544761 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0321. Min Act: -0.0005

Data Index: 1469514 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0301. Min Act: -0.0005

Data Index: 1407649 (Python Code)

Max Activating Token Index: 332

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0312. Min Act: -0.0005

Data Index: 1433910 (Python Code)

Max Activating Token Index: 356

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0305. Min Act: -0.0005

Data Index: 1559395 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0323. Min Act: -0.0005

Data Index: 1540781 (Python Code)

Max Activating Token Index: 740