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

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

Neuron 4740 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.4097. Min Act: -0.0000

Data Index: 941976 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3363. Min Act: -0.0000

Data Index: 742621 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3299. Min Act: 0.0000

Data Index: 900313 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2952. Min Act: -0.0000

Data Index: 26685 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2778. Min Act: -0.0000

Data Index: 860774 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2947. Min Act: -0.0000

Data Index: 222484 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2857. Min Act: -0.0000

Data Index: 264372 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2549. Min Act: -0.0000

Data Index: 904329 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1257557 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2536. Min Act: -0.0000

Data Index: 693629 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2517. Min Act: -0.0000

Data Index: 559249 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2493. Min Act: -0.0000

Data Index: 332210 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2369. Min Act: -0.0000

Data Index: 676889 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2434. Min Act: -0.0000

Data Index: 278867 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2424. Min Act: 0.0000

Data Index: 227428 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1191069 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2391. Min Act: 0.0001

Data Index: 1034702 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2437. Min Act: 0.0000

Data Index: 1289531 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2433. Min Act: 0.0000

Data Index: 405893 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2456. Min Act: -0.0000

Data Index: 657530 (C4 (Web Text))

Max Activating Token Index: 994