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

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

Neuron 401 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.7493. Min Act: -0.0001

Data Index: 604735 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1816. Min Act: -0.0001

Data Index: 463831 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.2035. Min Act: -0.0001

Data Index: 967489 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1192487 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.2228. Min Act: -0.0001

Data Index: 1188219 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1580. Min Act: -0.0001

Data Index: 784889 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1071. Min Act: -0.0001

Data Index: 818131 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1412. Min Act: -0.0001

Data Index: 642396 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1514. Min Act: -0.0001

Data Index: 212039 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1325. Min Act: -0.0001

Data Index: 935844 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.0960. Min Act: -0.0001

Data Index: 1344280 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1252. Min Act: -0.0001

Data Index: 1089756 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1205. Min Act: -0.0001

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1069. Min Act: -0.0001

Data Index: 749637 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1171. Min Act: -0.0001

Data Index: 720811 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.0288. Min Act: -0.0001

Data Index: 912377 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1193. Min Act: -0.0001

Data Index: 1080305 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.0584. Min Act: -0.0001

Data Index: 1181793 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1569. Min Act: -0.0001

Data Index: 547504 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.0164. Min Act: -0.0001

Data Index: 396950 (C4 (Web Text))

Max Activating Token Index: 913