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

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

Neuron 3508 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.4644. Min Act: -0.0001

Data Index: 830543 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.3479. Min Act: -0.0001

Data Index: 985527 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2788. Min Act: -0.0001

Data Index: 257478 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2941. Min Act: -0.0000

Data Index: 357710 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2918. Min Act: -0.0001

Data Index: 1262475 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2765. Min Act: -0.0001

Data Index: 797196 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2821. Min Act: -0.0001

Data Index: 451050 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2495. Min Act: -0.0000

Data Index: 509424 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2116. Min Act: -0.0001

Data Index: 755008 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2582. Min Act: -0.0001

Data Index: 422639 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2425. Min Act: -0.0001

Data Index: 366621 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2365. Min Act: -0.0001

Data Index: 445537 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2611. Min Act: -0.0001

Data Index: 135293 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2264. Min Act: -0.0000

Data Index: 339637 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1318575 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1290128 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1239905 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1087291 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2398. Min Act: -0.0001

Data Index: 654106 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.4644. Min Range: -0.4644

Max Act: 0.2365. Min Act: -0.0001

Data Index: 26266 (C4 (Web Text))

Max Activating Token Index: 448