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

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

Neuron 3011 in Layer 0

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: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0001

Data Index: 904157 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0437. Min Act: -0.0001

Data Index: 889312 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0423. Min Act: -0.0001

Data Index: 217343 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0386. Min Act: -0.0001

Data Index: 650284 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0370. Min Act: -0.0001

Data Index: 912666 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1498502 (Python Code)

Max Activating Token Index: 504

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0375. Min Act: -0.0001

Data Index: 536 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0375. Min Act: -0.0001

Data Index: 383203 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0370. Min Act: -0.0002

Data Index: 170209 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1009569 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0365. Min Act: -0.0001

Data Index: 495785 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0364. Min Act: -0.0001

Data Index: 508613 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1236109 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0361. Min Act: -0.0001

Data Index: 704661 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1483771 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1137848 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1411445 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0351. Min Act: -0.0001

Data Index: 61659 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0351. Min Act: -0.0001

Data Index: 88370 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1093264 (C4 (Web Text))

Max Activating Token Index: 29