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

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

Neuron 827 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1733. Min Act: -0.0000

Data Index: 752270 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1720. Min Act: -0.0000

Data Index: 320266 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1529. Min Act: -0.0000

Data Index: 941134 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1450. Min Act: -0.0000

Data Index: 314470 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1427. Min Act: -0.0001

Data Index: 11262 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1442. Min Act: -0.0000

Data Index: 884996 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1356. Min Act: -0.0000

Data Index: 740241 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1347. Min Act: -0.0000

Data Index: 392641 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1345. Min Act: -0.0001

Data Index: 698733 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1331. Min Act: -0.0000

Data Index: 951871 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1308. Min Act: -0.0000

Data Index: 749123 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1325854 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1230. Min Act: -0.0001

Data Index: 983410 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1193. Min Act: -0.0000

Data Index: 30729 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1181. Min Act: -0.0000

Data Index: 488624 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1171993 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1129. Min Act: -0.0000

Data Index: 502862 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1149486 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1078. Min Act: -0.0000

Data Index: 711569 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1022795 (C4 (Web Text))

Max Activating Token Index: 379