Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2667. Min Act: -0.0001

Data Index: 1547454 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2437. Min Act: -0.0001

Data Index: 1543968 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1374408 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2313. Min Act: -0.0001

Data Index: 1375553 (Python Code)

Max Activating Token Index: 415

Text #4

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2350. Min Act: -0.0001

Data Index: 1437191 (Python Code)

Max Activating Token Index: 467

Text #5

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1634562 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1475001 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1562880 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2065. Min Act: -0.0001

Data Index: 949091 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1376989 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2030. Min Act: -0.0001

Data Index: 494099 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1422918 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1012114 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1894. Min Act: -0.0001

Data Index: 320128 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1891. Min Act: -0.0000

Data Index: 665554 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1366585 (Python Code)

Max Activating Token Index: 477

Text #16

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1934. Min Act: -0.0001

Data Index: 984304 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1592590 (Python Code)

Max Activating Token Index: 693

Text #18

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1628777 (Python Code)

Max Activating Token Index: 411

Text #19

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1751. Min Act: -0.0001

Data Index: 406131 (C4 (Web Text))

Max Activating Token Index: 46