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

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

Neuron 3647 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: 0.1672. Min Range: -0.1672

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1138377 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1140308 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1172795 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1462. Min Act: -0.0001

Data Index: 1349694 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1622. Min Act: -0.0001

Data Index: 77235 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1557. Min Act: -0.0001

Data Index: 900846 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1066836 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1369. Min Act: -0.0001

Data Index: 22304 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1098373 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1339. Min Act: -0.0001

Data Index: 43788 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1133777 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1291916 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1134926 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1238382 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1308. Min Act: -0.0001

Data Index: 613328 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1260. Min Act: -0.0001

Data Index: 445595 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1338. Min Act: -0.0001

Data Index: 37039 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1309. Min Act: -0.0001

Data Index: 456255 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1217. Min Act: -0.0001

Data Index: 280200 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1281. Min Act: -0.0001

Data Index: 740378 (C4 (Web Text))

Max Activating Token Index: 492