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

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

Neuron 621 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9055. Min Act: -0.0000

Data Index: 1643560 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9921. Min Act: -0.0000

Data Index: 1472753 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1420532 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9583. Min Act: -0.0000

Data Index: 1517535 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9097. Min Act: -0.0001

Data Index: 1630423 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9200. Min Act: -0.0000

Data Index: 1497099 (Python Code)

Max Activating Token Index: 951

Text #6

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9143. Min Act: -0.0001

Data Index: 1630739 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1596981 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.8942. Min Act: -0.0000

Data Index: 1439652 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9038. Min Act: -0.0000

Data Index: 1615497 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9066. Min Act: -0.0000

Data Index: 1460063 (Python Code)

Max Activating Token Index: 962

Text #11

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1632051 (Python Code)

Max Activating Token Index: 362

Text #12

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9903. Min Act: -0.0000

Data Index: 1604155 (Python Code)

Max Activating Token Index: 472

Text #13

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.7947. Min Act: -0.0000

Data Index: 1575615 (Python Code)

Max Activating Token Index: 1017

Text #14

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.8820. Min Act: -0.0000

Data Index: 1614106 (Python Code)

Max Activating Token Index: 636

Text #15

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.8865. Min Act: -0.0000

Data Index: 1589571 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.8915. Min Act: -0.0000

Data Index: 1606757 (Python Code)

Max Activating Token Index: 616

Text #17

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9075. Min Act: -0.0000

Data Index: 1617689 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.8895. Min Act: -0.0000

Data Index: 1456231 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 1.9930. Min Range: -1.9930

Max Act: 1.9791. Min Act: -0.0000

Data Index: 1362261 (Python Code)

Max Activating Token Index: 334