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

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

Neuron 3972 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1488918 (Python Code)

Max Activating Token Index: 286

Text #1

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9260. Min Act: -0.0000

Data Index: 841208 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1524678 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1516391 (Python Code)

Max Activating Token Index: 378

Text #4

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8013. Min Act: -0.0000

Data Index: 929216 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1510402 (Python Code)

Max Activating Token Index: 947

Text #6

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1077069 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1620373 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7571. Min Act: -0.0000

Data Index: 200851 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1599972 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1306924 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1603368 (Python Code)

Max Activating Token Index: 283

Text #12

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1630785 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7227. Min Act: -0.0000

Data Index: 630574 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.6572. Min Act: -0.0000

Data Index: 629992 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1365500 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1401393 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1438696 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.6627. Min Act: -0.0000

Data Index: 538459 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1476454 (Python Code)

Max Activating Token Index: 130