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

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

Neuron 652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2717. Min Act: -0.0001

Data Index: 206035 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.3111. Min Act: -0.0001

Data Index: 1138245 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2835. Min Act: -0.0001

Data Index: 1154459 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2865. Min Act: -0.0001

Data Index: 1065818 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2423. Min Act: -0.0001

Data Index: 468052 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2433. Min Act: -0.0001

Data Index: 1046021 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2541. Min Act: -0.0001

Data Index: 697784 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2360. Min Act: -0.0001

Data Index: 871852 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2472. Min Act: -0.0001

Data Index: 144157 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1108801 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.1990. Min Act: -0.0001

Data Index: 1217064 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2180. Min Act: -0.0001

Data Index: 736390 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1248184 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.1928. Min Act: -0.0001

Data Index: 896507 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2228. Min Act: -0.0001

Data Index: 658380 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2054. Min Act: -0.0001

Data Index: 15762 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2371. Min Act: -0.0001

Data Index: 149252 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2077. Min Act: -0.0001

Data Index: 102717 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2141. Min Act: -0.0001

Data Index: 189464 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2287. Min Act: -0.0001

Data Index: 1224236 (C4 (Web Text))

Max Activating Token Index: 895