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

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

Neuron 336 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: 0.3413. Min Range: -0.3413

Max Act: 0.3413. Min Act: -0.0001

Data Index: 500789 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3185. Min Act: -0.0000

Data Index: 414201 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3061. Min Act: -0.0001

Data Index: 472933 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.3052. Min Act: -0.0000

Data Index: 61321 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2978. Min Act: -0.0001

Data Index: 614379 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2833. Min Act: -0.0001

Data Index: 1085166 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2736. Min Act: -0.0001

Data Index: 511325 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2737. Min Act: -0.0001

Data Index: 809467 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2705. Min Act: -0.0001

Data Index: 304769 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2706. Min Act: -0.0001

Data Index: 696612 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2551. Min Act: -0.0001

Data Index: 922998 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2502. Min Act: -0.0001

Data Index: 989310 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2506. Min Act: -0.0000

Data Index: 294865 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1145478 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2443. Min Act: -0.0001

Data Index: 1351435 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2260. Min Act: -0.0000

Data Index: 139184 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2417. Min Act: -0.0000

Data Index: 343704 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2320. Min Act: -0.0001

Data Index: 555771 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2366. Min Act: -0.0001

Data Index: 90675 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.3413. Min Range: -0.3413

Max Act: 0.2309. Min Act: -0.0001

Data Index: 730506 (C4 (Web Text))

Max Activating Token Index: 60