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

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

Neuron 4485 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2769. Min Act: -0.0000

Data Index: 695357 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2753. Min Act: -0.0000

Data Index: 822042 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2700. Min Act: -0.0000

Data Index: 427578 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2629. Min Act: -0.0000

Data Index: 942356 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2465. Min Act: -0.0000

Data Index: 485033 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2428. Min Act: -0.0000

Data Index: 97488 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1068870 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2493. Min Act: -0.0000

Data Index: 507340 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1087124 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1009238 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1195327 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2423. Min Act: -0.0000

Data Index: 449329 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2278. Min Act: -0.0000

Data Index: 65759 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2457. Min Act: -0.0000

Data Index: 899365 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1130901 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1237805 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1105099 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1079057 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2327. Min Act: -0.0000

Data Index: 429194 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2391. Min Act: -0.0000

Data Index: 52487 (C4 (Web Text))

Max Activating Token Index: 413