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

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

Neuron 3717 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2561. Min Act: -0.0000

Data Index: 259932 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2644. Min Act: -0.0000

Data Index: 70130 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2513. Min Act: -0.0000

Data Index: 72568 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2423. Min Act: -0.0001

Data Index: 150223 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1325430 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2375. Min Act: -0.0000

Data Index: 487768 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1330156 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2372. Min Act: -0.0001

Data Index: 750645 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2279. Min Act: -0.0000

Data Index: 586168 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2170. Min Act: -0.0000

Data Index: 59093 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2054. Min Act: -0.0000

Data Index: 416993 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2047. Min Act: -0.0000

Data Index: 507850 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2155. Min Act: -0.0001

Data Index: 383827 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2138. Min Act: -0.0000

Data Index: 30190 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1228639 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2060. Min Act: -0.0001

Data Index: 278241 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2094. Min Act: -0.0000

Data Index: 675558 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2089. Min Act: -0.0000

Data Index: 980641 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2050. Min Act: -0.0000

Data Index: 160643 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2000. Min Act: -0.0000

Data Index: 170637 (C4 (Web Text))

Max Activating Token Index: 53