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

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

Neuron 358 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: 1.1980. Min Range: -1.1980

Max Act: 1.1795. Min Act: -0.0001

Data Index: 929137 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.1980. Min Range: -1.1980

Max Act: 1.1374. Min Act: -0.0001

Data Index: 1338839 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 1.1980. Min Range: -1.1980

Max Act: 1.1980. Min Act: -0.0001

Data Index: 817772 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.1980. Min Range: -1.1980

Max Act: 1.1272. Min Act: -0.0001

Data Index: 33295 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.1980. Min Range: -1.1980

Max Act: 1.0617. Min Act: -0.0001

Data Index: 1240816 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 1.1980. Min Range: -1.1980

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1013971 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9971. Min Act: -0.0001

Data Index: 1156612 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.1980. Min Range: -1.1980

Max Act: 1.0130. Min Act: -0.0001

Data Index: 222178 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.1980. Min Range: -1.1980

Max Act: 1.0326. Min Act: -0.0001

Data Index: 841900 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9486. Min Act: -0.0001

Data Index: 290719 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9286. Min Act: -0.0001

Data Index: 490095 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9641. Min Act: -0.0001

Data Index: 1226392 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9967. Min Act: -0.0001

Data Index: 680367 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.8814. Min Act: -0.0001

Data Index: 1092367 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9047. Min Act: -0.0001

Data Index: 548134 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9238. Min Act: -0.0001

Data Index: 351473 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1059542 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9171. Min Act: -0.0001

Data Index: 3202 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.9213. Min Act: -0.0001

Data Index: 508231 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 1.1980. Min Range: -1.1980

Max Act: 0.8037. Min Act: -0.0001

Data Index: 633111 (C4 (Web Text))

Max Activating Token Index: 780