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

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

Neuron 3511 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.8087. Min Act: -0.0000

Data Index: 747881 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.6121. Min Act: -0.0000

Data Index: 329054 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.6285. Min Act: -0.0000

Data Index: 631490 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.5894. Min Act: -0.0000

Data Index: 1169201 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.0537. Min Act: -0.0000

Data Index: 341056 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.5006. Min Act: -0.0000

Data Index: 890187 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.2325. Min Act: -0.0000

Data Index: 836896 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.2154. Min Act: -0.0000

Data Index: 1055295 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.2116. Min Act: -0.0000

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.9751. Min Act: -0.0000

Data Index: 1164574 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.9823. Min Act: -0.0000

Data Index: 1173083 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.0407. Min Act: -0.0000

Data Index: 1029125 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.0095. Min Act: -0.0000

Data Index: 934963 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.1916. Min Act: -0.0000

Data Index: 1218840 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.7747. Min Act: -0.0000

Data Index: 549442 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.9256. Min Act: -0.0000

Data Index: 460508 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.8938. Min Act: -0.0000

Data Index: 416050 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.2255. Min Act: -0.0000

Data Index: 522905 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.9681. Min Act: -0.0000

Data Index: 935059 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.6055. Min Act: -0.0000

Data Index: 65180 (C4 (Web Text))

Max Activating Token Index: 471