Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3202 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1170819 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0001

Data Index: 245311 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0502. Min Act: -0.0001

Data Index: 605459 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0505. Min Act: -0.0001

Data Index: 121299 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0491. Min Act: -0.0001

Data Index: 10353 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1022973 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0463. Min Act: -0.0001

Data Index: 735472 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0466. Min Act: -0.0001

Data Index: 555380 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0381. Min Act: -0.0001

Data Index: 102503 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1314161 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0476. Min Act: -0.0001

Data Index: 628996 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0429. Min Act: -0.0001

Data Index: 44222 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0444. Min Act: -0.0001

Data Index: 865353 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0450. Min Act: -0.0001

Data Index: 781875 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0398. Min Act: -0.0001

Data Index: 836563 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0438. Min Act: -0.0001

Data Index: 638930 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0410. Min Act: -0.0001

Data Index: 627722 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0418. Min Act: -0.0001

Data Index: 590154 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0394. Min Act: -0.0001

Data Index: 246654 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0403. Min Act: -0.0001

Data Index: 702361 (C4 (Web Text))

Max Activating Token Index: 321