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

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

Neuron 918 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2265. Min Act: -0.0000

Data Index: 195278 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2154. Min Act: -0.0000

Data Index: 237102 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2012. Min Act: -0.0000

Data Index: 154051 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1887. Min Act: -0.0000

Data Index: 309977 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1317277 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1765. Min Act: -0.0000

Data Index: 131075 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1321678 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1598. Min Act: -0.0000

Data Index: 286483 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1620. Min Act: -0.0000

Data Index: 667192 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1662. Min Act: -0.0000

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1246167 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1430. Min Act: -0.0000

Data Index: 255911 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1066144 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1406. Min Act: -0.0000

Data Index: 718800 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1165449 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1465. Min Act: -0.0000

Data Index: 16272 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1425. Min Act: -0.0000

Data Index: 689147 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1167750 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1340. Min Act: -0.0000

Data Index: 446421 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1287. Min Act: -0.0000

Data Index: 503539 (C4 (Web Text))

Max Activating Token Index: 148