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

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

Neuron 1084 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: 12.9700. Min Range: -12.9700

Max Act: 12.8786. Min Act: -0.0001

Data Index: 1393231 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.9700. Min Act: -0.0001

Data Index: 1523484 (Python Code)

Max Activating Token Index: 506

Text #2

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.7194. Min Act: -0.0001

Data Index: 1632928 (Python Code)

Max Activating Token Index: 496

Text #3

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.4395. Min Act: -0.0001

Data Index: 1598811 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.5221. Min Act: -0.0001

Data Index: 1454949 (Python Code)

Max Activating Token Index: 388

Text #5

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.4195. Min Act: -0.0001

Data Index: 1236847 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.3548. Min Act: -0.0001

Data Index: 1464423 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.3168. Min Act: -0.0001

Data Index: 1387539 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.2342. Min Act: -0.0001

Data Index: 1564090 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.0938. Min Act: -0.0001

Data Index: 1442156 (Python Code)

Max Activating Token Index: 350

Text #10

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.2376. Min Act: -0.0001

Data Index: 1469380 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.0318. Min Act: -0.0001

Data Index: 1589428 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 12.9700. Min Range: -12.9700

Max Act: 12.0127. Min Act: -0.0001

Data Index: 1651282 (Python Code)

Max Activating Token Index: 400

Text #13

Max Range: 12.9700. Min Range: -12.9700

Max Act: 11.9663. Min Act: -0.0001

Data Index: 1560400 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 12.9700. Min Range: -12.9700

Max Act: 11.9124. Min Act: -0.0001

Data Index: 1618831 (Python Code)

Max Activating Token Index: 495

Text #15

Max Range: 12.9700. Min Range: -12.9700

Max Act: 11.8668. Min Act: -0.0001

Data Index: 384535 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 12.9700. Min Range: -12.9700

Max Act: 11.9550. Min Act: -0.0001

Data Index: 1437428 (Python Code)

Max Activating Token Index: 520

Text #17

Max Range: 12.9700. Min Range: -12.9700

Max Act: 11.6873. Min Act: -0.0001

Data Index: 1577364 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 12.9700. Min Range: -12.9700

Max Act: 11.5335. Min Act: -0.0001

Data Index: 847215 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 12.9700. Min Range: -12.9700

Max Act: 11.6184. Min Act: -0.0001

Data Index: 1609229 (Python Code)

Max Activating Token Index: 672