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

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

Neuron 3517 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2776. Min Act: -0.0000

Data Index: 239408 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2680. Min Act: -0.0000

Data Index: 622060 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2775. Min Act: -0.0000

Data Index: 987718 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2560. Min Act: -0.0000

Data Index: 341253 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2747. Min Act: -0.0001

Data Index: 1043784 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1169608 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2571. Min Act: -0.0000

Data Index: 799354 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2564. Min Act: -0.0000

Data Index: 86065 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1036459 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2364. Min Act: -0.0000

Data Index: 338858 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1349665 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2512. Min Act: -0.0000

Data Index: 364923 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2391. Min Act: -0.0000

Data Index: 703512 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2463. Min Act: -0.0001

Data Index: 581652 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2364. Min Act: -0.0000

Data Index: 143119 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2358. Min Act: -0.0000

Data Index: 938583 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2365. Min Act: -0.0000

Data Index: 470911 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1075462 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1290536 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.2776. Min Range: -0.2776

Max Act: 0.2434. Min Act: -0.0001

Data Index: 315413 (C4 (Web Text))

Max Activating Token Index: 987