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

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

Neuron 5396 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: 0.9675. Min Range: -0.9675

Max Act: 0.9675. Min Act: -0.0000

Data Index: 71905 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1208123 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1001601 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8528. Min Act: -0.0000

Data Index: 888180 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8012. Min Act: -0.0000

Data Index: 528746 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7527. Min Act: -0.0000

Data Index: 729350 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1066040 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7442. Min Act: -0.0000

Data Index: 837807 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1529372 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7583. Min Act: -0.0000

Data Index: 497044 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7765. Min Act: -0.0000

Data Index: 777807 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7402. Min Act: -0.0000

Data Index: 559200 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7629. Min Act: -0.0000

Data Index: 289041 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1134072 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7344. Min Act: -0.0000

Data Index: 73921 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7356. Min Act: -0.0000

Data Index: 319890 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7571. Min Act: -0.0000

Data Index: 366553 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1328001 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1158773 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.7049. Min Act: -0.0000

Data Index: 149049 (C4 (Web Text))

Max Activating Token Index: 648