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

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

Neuron 2231 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0000

Data Index: 179911 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0475. Min Act: -0.0000

Data Index: 1385628 (Python Code)

Max Activating Token Index: 397

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0460. Min Act: -0.0000

Data Index: 225105 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1564233 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1507446 (Python Code)

Max Activating Token Index: 145

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0408. Min Act: -0.0000

Data Index: 1389275 (Python Code)

Max Activating Token Index: 416

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0436. Min Act: -0.0000

Data Index: 856740 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0416. Min Act: -0.0000

Data Index: 607765 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0414. Min Act: -0.0000

Data Index: 917785 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0409. Min Act: -0.0000

Data Index: 1491188 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1130882 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0384. Min Act: -0.0000

Data Index: 647635 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1566100 (Python Code)

Max Activating Token Index: 354

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0395. Min Act: -0.0000

Data Index: 767763 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0393. Min Act: -0.0000

Data Index: 861908 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0343. Min Act: -0.0000

Data Index: 1049267 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0383. Min Act: -0.0000

Data Index: 653528 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0336. Min Act: -0.0000

Data Index: 18744 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0360. Min Act: -0.0000

Data Index: 223318 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0332. Min Act: -0.0000

Data Index: 630322 (C4 (Web Text))

Max Activating Token Index: 995