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

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

Neuron 388 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1174322 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2681. Min Act: -0.0001

Data Index: 284446 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2587. Min Act: -0.0001

Data Index: 532363 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2590. Min Act: -0.0001

Data Index: 730649 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1018492 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2529. Min Act: -0.0001

Data Index: 1011399 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2612. Min Act: -0.0000

Data Index: 875426 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2570. Min Act: -0.0001

Data Index: 853897 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2510. Min Act: -0.0001

Data Index: 491532 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1025957 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1150807 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2375. Min Act: -0.0001

Data Index: 489929 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1015622 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1182927 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2398. Min Act: -0.0001

Data Index: 904883 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2248. Min Act: -0.0001

Data Index: 1283215 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2253. Min Act: -0.0001

Data Index: 498101 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2322. Min Act: -0.0001

Data Index: 372919 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2317. Min Act: -0.0001

Data Index: 369863 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2218. Min Act: -0.0000

Data Index: 529241 (C4 (Web Text))

Max Activating Token Index: 390