Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3990 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1227028 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8911. Min Act: -0.0001

Data Index: 1237116 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7765. Min Act: -0.0000

Data Index: 680157 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8617. Min Act: -0.0000

Data Index: 499640 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7810. Min Act: -0.0001

Data Index: 692365 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1534136 (Python Code)

Max Activating Token Index: 629

Text #6

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8070. Min Act: -0.0001

Data Index: 53108 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8557. Min Act: -0.0001

Data Index: 817710 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8328. Min Act: -0.0000

Data Index: 298333 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7799. Min Act: -0.0001

Data Index: 148268 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1101426 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1399622 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7601. Min Act: -0.0000

Data Index: 137954 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1117592 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8605. Min Act: -0.0000

Data Index: 724748 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7512. Min Act: -0.0001

Data Index: 1083276 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1377853 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1127822 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.7585. Min Act: -0.0001

Data Index: 127902 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.9173. Min Range: -0.9173

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1187696 (C4 (Web Text))

Max Activating Token Index: 410