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

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

Neuron 3644 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: 1.6080. Min Range: -1.6080

Max Act: 1.5807. Min Act: -0.0001

Data Index: 924406 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.6080. Min Act: -0.0001

Data Index: 1215324 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.4580. Min Act: -0.0001

Data Index: 800127 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.3191. Min Act: -0.0001

Data Index: 1220499 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2929. Min Act: -0.0001

Data Index: 498996 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.4062. Min Act: -0.0001

Data Index: 1314182 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.3797. Min Act: -0.0001

Data Index: 1219953 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2652. Min Act: -0.0001

Data Index: 425944 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1890. Min Act: -0.0001

Data Index: 1178712 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1925. Min Act: -0.0001

Data Index: 1047491 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1342. Min Act: -0.0001

Data Index: 567739 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2625. Min Act: -0.0001

Data Index: 362037 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.3484. Min Act: -0.0001

Data Index: 265386 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0951. Min Act: -0.0001

Data Index: 538812 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2304. Min Act: -0.0001

Data Index: 1333783 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0104. Min Act: -0.0001

Data Index: 1320089 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1463. Min Act: -0.0001

Data Index: 599437 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1616. Min Act: -0.0001

Data Index: 317311 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1328. Min Act: -0.0001

Data Index: 104586 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1245. Min Act: -0.0001

Data Index: 477577 (C4 (Web Text))

Max Activating Token Index: 240