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

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

Neuron 94 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0055. Min Act: -0.0004

Data Index: 1368412 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0030. Min Act: -0.0004

Data Index: 1359927 (Python Code)

Max Activating Token Index: 688

Text #2

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0031. Min Act: -0.0004

Data Index: 241278 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0029. Min Act: -0.0004

Data Index: 1008562 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0029. Min Act: -0.0004

Data Index: 1371794 (Python Code)

Max Activating Token Index: 1011

Text #5

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0029. Min Act: -0.0004

Data Index: 1588455 (Python Code)

Max Activating Token Index: 769

Text #6

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0028. Min Act: -0.0004

Data Index: 1359334 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0028. Min Act: -0.0004

Data Index: 325685 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0028. Min Act: -0.0004

Data Index: 1058696 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0027. Min Act: -0.0004

Data Index: 123528 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0027. Min Act: -0.0004

Data Index: 1528432 (Python Code)

Max Activating Token Index: 922

Text #11

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0027. Min Act: -0.0004

Data Index: 863288 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0025. Min Act: -0.0004

Data Index: 937413 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0026. Min Act: -0.0004

Data Index: 449925 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0027. Min Act: -0.0004

Data Index: 1593354 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0026. Min Act: -0.0004

Data Index: 1388406 (Python Code)

Max Activating Token Index: 853

Text #16

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0024. Min Act: -0.0004

Data Index: 1184479 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0025. Min Act: -0.0004

Data Index: 255696 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0026. Min Act: -0.0004

Data Index: 1451719 (Python Code)

Max Activating Token Index: 986

Text #19

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0025. Min Act: -0.0004

Data Index: 1402427 (Python Code)

Max Activating Token Index: 1002