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

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

Neuron 3511 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.3049. Min Act: -0.0000

Data Index: 499150 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1034461 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.3068. Min Act: -0.0000

Data Index: 446341 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.3047. Min Act: -0.0000

Data Index: 146228 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2706. Min Act: -0.0000

Data Index: 216964 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2842. Min Act: -0.0000

Data Index: 746433 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2778. Min Act: -0.0001

Data Index: 174713 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2654. Min Act: -0.0001

Data Index: 147268 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2609. Min Act: -0.0000

Data Index: 781791 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2702. Min Act: -0.0000

Data Index: 31386 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2691. Min Act: -0.0001

Data Index: 724417 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2565. Min Act: -0.0001

Data Index: 940508 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1203533 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1328679 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2443. Min Act: -0.0000

Data Index: 373293 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2374. Min Act: -0.0000

Data Index: 638463 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2234. Min Act: -0.0000

Data Index: 285399 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2353. Min Act: -0.0000

Data Index: 973650 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2354. Min Act: -0.0000

Data Index: 187363 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2339. Min Act: -0.0000

Data Index: 990948 (C4 (Web Text))

Max Activating Token Index: 909