Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2098 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1346. Min Act: -0.0001

Data Index: 690610 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1226. Min Act: -0.0001

Data Index: 675964 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1161. Min Act: -0.0001

Data Index: 622672 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1288936 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1072. Min Act: -0.0001

Data Index: 612594 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1121. Min Act: -0.0001

Data Index: 418316 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0996. Min Act: -0.0001

Data Index: 450163 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1035. Min Act: -0.0001

Data Index: 7476 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1035182 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1159844 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0974. Min Act: -0.0001

Data Index: 779714 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0990. Min Act: -0.0001

Data Index: 861966 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0903. Min Act: -0.0001

Data Index: 80706 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0893. Min Act: -0.0001

Data Index: 59901 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1124958 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1231476 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0891. Min Act: -0.0001

Data Index: 702783 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1049389 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0879. Min Act: -0.0001

Data Index: 669439 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0919. Min Act: -0.0001

Data Index: 869735 (C4 (Web Text))

Max Activating Token Index: 499