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

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

Neuron 329 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: 0.9648. Min Range: -0.9648

Max Act: 0.9648. Min Act: -0.0001

Data Index: 971540 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8799. Min Act: -0.0002

Data Index: 1234387 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9369. Min Act: -0.0002

Data Index: 342072 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9006. Min Act: -0.0001

Data Index: 1435701 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9222. Min Act: -0.0002

Data Index: 1132978 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1620399 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9069. Min Act: -0.0001

Data Index: 1484149 (Python Code)

Max Activating Token Index: 286

Text #7

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8568. Min Act: -0.0002

Data Index: 941690 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8257. Min Act: -0.0001

Data Index: 275030 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8381. Min Act: -0.0002

Data Index: 827734 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8619. Min Act: -0.0001

Data Index: 832027 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8620. Min Act: -0.0001

Data Index: 438260 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9111. Min Act: -0.0001

Data Index: 1072425 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9038. Min Act: -0.0001

Data Index: 1434198 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9067. Min Act: -0.0001

Data Index: 1102170 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8394. Min Act: -0.0002

Data Index: 44454 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8736. Min Act: -0.0001

Data Index: 766307 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8911. Min Act: -0.0001

Data Index: 1155621 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8669. Min Act: -0.0001

Data Index: 1458982 (Python Code)

Max Activating Token Index: 989

Text #19

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8595. Min Act: -0.0002

Data Index: 1339851 (C4 (Web Text))

Max Activating Token Index: 231