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

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

Neuron 33 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.9919. Min Act: -0.0000

Data Index: 1440291 (Python Code)

Max Activating Token Index: 884

Text #1

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.8091. Min Act: -0.0000

Data Index: 1494552 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.5896. Min Act: -0.0000

Data Index: 1537754 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.7101. Min Act: -0.0000

Data Index: 1595450 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.3951. Min Act: -0.0000

Data Index: 1384410 (Python Code)

Max Activating Token Index: 905

Text #5

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.4994. Min Act: -0.0000

Data Index: 1505990 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.9059. Min Act: -0.0000

Data Index: 1441868 (Python Code)

Max Activating Token Index: 951

Text #7

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.6180. Min Act: -0.0000

Data Index: 1570975 (Python Code)

Max Activating Token Index: 595

Text #8

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.2015. Min Act: -0.0000

Data Index: 1552496 (Python Code)

Max Activating Token Index: 886

Text #9

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.4335. Min Act: -0.0000

Data Index: 1414163 (Python Code)

Max Activating Token Index: 939

Text #10

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.4160. Min Act: -0.0000

Data Index: 1603433 (Python Code)

Max Activating Token Index: 969

Text #11

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.6613. Min Act: -0.0000

Data Index: 1393606 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.6668. Min Act: -0.0000

Data Index: 1454971 (Python Code)

Max Activating Token Index: 1010

Text #13

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.3779. Min Act: -0.0000

Data Index: 1505669 (Python Code)

Max Activating Token Index: 226

Text #14

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.4714. Min Act: -0.0000

Data Index: 1606020 (Python Code)

Max Activating Token Index: 764

Text #15

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.4801. Min Act: -0.0000

Data Index: 1586326 (Python Code)

Max Activating Token Index: 876

Text #16

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.3187. Min Act: -0.0000

Data Index: 1457124 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.3190. Min Act: -0.0000

Data Index: 1371004 (Python Code)

Max Activating Token Index: 1013

Text #18

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.1954. Min Act: -0.0000

Data Index: 1655046 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 2.9919. Min Range: -2.9919

Max Act: 2.4484. Min Act: -0.0000

Data Index: 1649654 (Python Code)

Max Activating Token Index: 787