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

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

Neuron 2655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2526. Min Range: -5.2526

Max Act: 5.2526. Min Act: -0.0001

Data Index: 251624 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.4859. Min Act: -0.0001

Data Index: 70146 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.4852. Min Act: -0.0001

Data Index: 687249 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.3952. Min Act: -0.0001

Data Index: 861155 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.1223. Min Act: -0.0001

Data Index: 689906 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.3005. Min Act: -0.0001

Data Index: 493876 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.9938. Min Act: -0.0001

Data Index: 913263 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.9884. Min Act: -0.0001

Data Index: 820394 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.1296. Min Act: -0.0001

Data Index: 821525 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.8169. Min Act: -0.0001

Data Index: 583199 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.9697. Min Act: -0.0001

Data Index: 899925 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 5.2526. Min Range: -5.2526

Max Act: 4.0986. Min Act: -0.0001

Data Index: 22508 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.6802. Min Act: -0.0001

Data Index: 910877 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.8265. Min Act: -0.0001

Data Index: 1260859 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.7986. Min Act: -0.0001

Data Index: 200589 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.7569. Min Act: -0.0001

Data Index: 474947 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.7384. Min Act: -0.0001

Data Index: 996410 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.1142. Min Act: -0.0001

Data Index: 258148 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.7245. Min Act: -0.0001

Data Index: 1093345 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 5.2526. Min Range: -5.2526

Max Act: 3.5334. Min Act: -0.0001

Data Index: 625645 (C4 (Web Text))

Max Activating Token Index: 113