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

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

Neuron 477 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: 0.2706. Min Range: -0.2706

Max Act: 0.2446. Min Act: -0.0001

Data Index: 1504111 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2321. Min Act: -0.0001

Data Index: 1586378 (Python Code)

Max Activating Token Index: 659

Text #2

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2706. Min Act: -0.0001

Data Index: 1528700 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1539418 (Python Code)

Max Activating Token Index: 628

Text #4

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2461. Min Act: -0.0001

Data Index: 1507911 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1481002 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1406278 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2281. Min Act: -0.0001

Data Index: 1498636 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1363661 (Python Code)

Max Activating Token Index: 900

Text #9

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2240. Min Act: -0.0001

Data Index: 103044 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1444851 (Python Code)

Max Activating Token Index: 604

Text #11

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2178. Min Act: -0.0001

Data Index: 1469931 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2296. Min Act: -0.0001

Data Index: 1407440 (Python Code)

Max Activating Token Index: 568

Text #13

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2200. Min Act: -0.0001

Data Index: 636944 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1609322 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2227. Min Act: -0.0001

Data Index: 1416672 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1567059 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1523284 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2172. Min Act: -0.0001

Data Index: 1521385 (Python Code)

Max Activating Token Index: 752

Text #19

Max Range: 0.2706. Min Range: -0.2706

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1642993 (Python Code)

Max Activating Token Index: 351