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

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

Neuron 1982 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: 0.1556. Min Range: -0.1556

Max Act: 0.1556. Min Act: -0.0002

Data Index: 348222 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1413. Min Act: -0.0002

Data Index: 439126 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1404. Min Act: -0.0003

Data Index: 415734 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1355772 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1358. Min Act: -0.0002

Data Index: 528301 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1354. Min Act: -0.0003

Data Index: 440652 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1031982 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1375. Min Act: -0.0002

Data Index: 849988 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1332. Min Act: -0.0002

Data Index: 64270 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1312. Min Act: -0.0002

Data Index: 384507 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1317. Min Act: -0.0002

Data Index: 390353 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1330. Min Act: -0.0003

Data Index: 771137 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1298. Min Act: -0.0002

Data Index: 832679 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1285. Min Act: -0.0002

Data Index: 348460 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1302. Min Act: -0.0003

Data Index: 435369 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1097461 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1292. Min Act: -0.0002

Data Index: 679441 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1254293 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1272. Min Act: -0.0002

Data Index: 642360 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1249. Min Act: -0.0002

Data Index: 70109 (C4 (Web Text))

Max Activating Token Index: 434