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

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

Neuron 2632 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: 0.1507. Min Range: -0.1507

Max Act: 0.1507. Min Act: -0.0002

Data Index: 216592 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1463. Min Act: -0.0002

Data Index: 456284 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1460. Min Act: -0.0002

Data Index: 138330 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1450. Min Act: -0.0002

Data Index: 847617 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1408. Min Act: -0.0002

Data Index: 818069 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1374. Min Act: -0.0002

Data Index: 285484 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1396. Min Act: -0.0002

Data Index: 512867 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1383. Min Act: -0.0002

Data Index: 952195 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1391. Min Act: -0.0002

Data Index: 536862 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1362. Min Act: -0.0002

Data Index: 968071 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1332. Min Act: -0.0002

Data Index: 163026 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1336. Min Act: -0.0002

Data Index: 701682 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1304356 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1317. Min Act: -0.0002

Data Index: 838920 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1354. Min Act: -0.0002

Data Index: 653674 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1313. Min Act: -0.0002

Data Index: 39206 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1341. Min Act: -0.0002

Data Index: 868723 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1311. Min Act: -0.0002

Data Index: 100400 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1277605 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1299. Min Act: -0.0002

Data Index: 1274375 (C4 (Web Text))

Max Activating Token Index: 14