Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1304 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0003

Data Index: 895562 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0700. Min Act: -0.0003

Data Index: 37114 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0631. Min Act: -0.0003

Data Index: 528968 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0561. Min Act: -0.0003

Data Index: 39714 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0529. Min Act: -0.0003

Data Index: 925148 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1072297 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0524. Min Act: -0.0003

Data Index: 681411 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0499. Min Act: -0.0003

Data Index: 521304 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0455. Min Act: -0.0003

Data Index: 785492 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1185246 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0488. Min Act: -0.0003

Data Index: 113488 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1087353 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0410. Min Act: -0.0003

Data Index: 798640 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0461. Min Act: -0.0003

Data Index: 773839 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0453. Min Act: -0.0003

Data Index: 303782 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1128968 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0478. Min Act: -0.0003

Data Index: 940199 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0402. Min Act: -0.0003

Data Index: 463435 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0444. Min Act: -0.0003

Data Index: 766346 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0409. Min Act: -0.0003

Data Index: 136448 (C4 (Web Text))

Max Activating Token Index: 355