Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 684 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1667. Min Act: -0.0002

Data Index: 1303385 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1653. Min Act: -0.0002

Data Index: 371795 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1670. Min Act: -0.0002

Data Index: 107617 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1501. Min Act: -0.0002

Data Index: 840268 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1486. Min Act: -0.0002

Data Index: 1017583 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1398. Min Act: -0.0002

Data Index: 399435 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1416. Min Act: -0.0002

Data Index: 106713 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1362. Min Act: -0.0002

Data Index: 873009 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1377. Min Act: -0.0002

Data Index: 481287 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1323. Min Act: -0.0002

Data Index: 701174 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1322. Min Act: -0.0002

Data Index: 1081853 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1328. Min Act: -0.0002

Data Index: 39959 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1326. Min Act: -0.0002

Data Index: 348104 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1291347 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1308. Min Act: -0.0002

Data Index: 558907 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1304. Min Act: -0.0002

Data Index: 571934 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1274. Min Act: -0.0002

Data Index: 1093471 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1305. Min Act: -0.0002

Data Index: 865629 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1292. Min Act: -0.0002

Data Index: 1226681 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1250054 (C4 (Web Text))

Max Activating Token Index: 840