Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1200 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.3077. Min Act: -0.0001

Data Index: 1273525 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2827. Min Act: -0.0001

Data Index: 850705 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2893. Min Act: -0.0001

Data Index: 674288 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2956. Min Act: -0.0001

Data Index: 1166293 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2734. Min Act: -0.0001

Data Index: 967355 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2502. Min Act: -0.0001

Data Index: 760420 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2547. Min Act: -0.0001

Data Index: 158556 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2545. Min Act: -0.0001

Data Index: 77453 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2442. Min Act: -0.0001

Data Index: 896009 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2413. Min Act: -0.0001

Data Index: 44283 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2377. Min Act: -0.0001

Data Index: 374669 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2325. Min Act: -0.0001

Data Index: 790478 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2406. Min Act: -0.0001

Data Index: 812891 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2493. Min Act: -0.0001

Data Index: 181821 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2417. Min Act: -0.0001

Data Index: 473800 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2391. Min Act: -0.0001

Data Index: 977524 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2286. Min Act: -0.0001

Data Index: 349364 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2460. Min Act: -0.0001

Data Index: 292718 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1137237 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.3077. Min Range: -0.3077

Max Act: 0.2397. Min Act: -0.0001

Data Index: 883234 (C4 (Web Text))

Max Activating Token Index: 752