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

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

Neuron 2629 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: 0.1379. Min Range: -0.1379

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1492923 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1379. Min Act: -0.0001

Data Index: 813721 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1242. Min Act: -0.0001

Data Index: 202153 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1227. Min Act: -0.0001

Data Index: 742769 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1344490 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1053. Min Act: -0.0001

Data Index: 13406 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1445307 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1159. Min Act: -0.0001

Data Index: 41799 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1043663 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1541105 (Python Code)

Max Activating Token Index: 549

Text #10

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1496406 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1650038 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1413220 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1569064 (Python Code)

Max Activating Token Index: 414

Text #14

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1093385 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1388712 (Python Code)

Max Activating Token Index: 295

Text #16

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1544059 (Python Code)

Max Activating Token Index: 632

Text #17

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1014. Min Act: -0.0001

Data Index: 657889 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1605967 (Python Code)

Max Activating Token Index: 741

Text #19

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1461336 (Python Code)

Max Activating Token Index: 341