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

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

Neuron 689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.4528. Min Act: -0.0001

Data Index: 584547 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.2448. Min Act: -0.0001

Data Index: 121877 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.1676. Min Act: -0.0001

Data Index: 1123204 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.2308. Min Act: -0.0002

Data Index: 407820 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.1984. Min Act: -0.0001

Data Index: 1302147 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.1481. Min Act: -0.0001

Data Index: 942551 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.2274. Min Act: -0.0001

Data Index: 436157 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.1149. Min Act: -0.0001

Data Index: 425890 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.0782. Min Act: -0.0001

Data Index: 327550 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.1050. Min Act: -0.0001

Data Index: 1007279 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.0587. Min Act: -0.0001

Data Index: 539865 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.0840. Min Act: -0.0001

Data Index: 82039 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.0551. Min Act: -0.0001

Data Index: 422746 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.0654. Min Act: -0.0001

Data Index: 1148522 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.0894. Min Act: -0.0001

Data Index: 674135 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.4528. Min Range: -1.4528

Max Act: 0.9801. Min Act: -0.0001

Data Index: 953505 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.0371. Min Act: -0.0001

Data Index: 154396 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.4528. Min Range: -1.4528

Max Act: 0.9865. Min Act: -0.0001

Data Index: 314330 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.4528. Min Range: -1.4528

Max Act: 1.0069. Min Act: -0.0001

Data Index: 807189 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.4528. Min Range: -1.4528

Max Act: 0.9461. Min Act: -0.0001

Data Index: 273795 (C4 (Web Text))

Max Activating Token Index: 199