Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 515 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1405430 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1471630 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1646082 (Python Code)

Max Activating Token Index: 603

Text #3

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1506134 (Python Code)

Max Activating Token Index: 285

Text #4

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7801. Min Act: -0.0000

Data Index: 186047 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7293. Min Act: -0.0000

Data Index: 843688 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1477240 (Python Code)

Max Activating Token Index: 862

Text #7

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1388052 (Python Code)

Max Activating Token Index: 960

Text #8

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1486459 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1483229 (Python Code)

Max Activating Token Index: 486

Text #10

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6975. Min Act: -0.0000

Data Index: 454193 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1587799 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1536388 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6730. Min Act: 0.0001

Data Index: 55750 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6531. Min Act: -0.0000

Data Index: 626403 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1547197 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6292. Min Act: -0.0000

Data Index: 414639 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6605. Min Act: 0.0000

Data Index: 268025 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1637379 (Python Code)

Max Activating Token Index: 300

Text #19

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1066564 (C4 (Web Text))

Max Activating Token Index: 454