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

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

Neuron 447 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2150. Min Act: -0.0001

Data Index: 795681 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1975. Min Act: -0.0001

Data Index: 468053 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1888. Min Act: -0.0001

Data Index: 655399 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1255789 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1228352 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1758. Min Act: -0.0001

Data Index: 970342 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1910. Min Act: -0.0001

Data Index: 234034 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1109688 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1781. Min Act: -0.0001

Data Index: 472466 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1224544 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1304023 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1321650 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1446. Min Act: -0.0001

Data Index: 190681 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1665. Min Act: -0.0001

Data Index: 914367 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1292194 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1678. Min Act: -0.0001

Data Index: 836281 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1623. Min Act: -0.0001

Data Index: 138593 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1266198 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1491. Min Act: -0.0001

Data Index: 249558 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1531. Min Act: -0.0001

Data Index: 736770 (C4 (Web Text))

Max Activating Token Index: 670