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

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

Neuron 3453 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: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0002

Data Index: 978095 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1145578 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0551. Min Act: -0.0002

Data Index: 537326 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1041280 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1144739 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1379563 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1153297 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0494. Min Act: -0.0003

Data Index: 702854 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0481. Min Act: -0.0002

Data Index: 943492 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0472. Min Act: -0.0002

Data Index: 119582 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0474. Min Act: -0.0002

Data Index: 411550 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1373294 (Python Code)

Max Activating Token Index: 442

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0470. Min Act: -0.0002

Data Index: 866359 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1292323 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1309660 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0460. Min Act: -0.0002

Data Index: 946110 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0467. Min Act: -0.0002

Data Index: 860621 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0460. Min Act: -0.0002

Data Index: 786650 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1307853 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0465. Min Act: -0.0002

Data Index: 244317 (C4 (Web Text))

Max Activating Token Index: 933