Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2791 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3482. Min Act: -0.0000

Data Index: 752216 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2982. Min Act: -0.0000

Data Index: 288410 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1009347 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2861. Min Act: -0.0000

Data Index: 250908 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2732. Min Act: -0.0000

Data Index: 441608 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2717. Min Act: -0.0000

Data Index: 859101 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1331363 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2808. Min Act: 0.0000

Data Index: 879001 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1157495 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1093207 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2449. Min Act: -0.0000

Data Index: 80556 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2568. Min Act: -0.0000

Data Index: 709173 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2458. Min Act: -0.0000

Data Index: 108855 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1346255 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2459. Min Act: -0.0000

Data Index: 108874 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1246060 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2417. Min Act: -0.0000

Data Index: 370306 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1276073 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2474. Min Act: -0.0000

Data Index: 938250 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2356. Min Act: 0.0000

Data Index: 1129723 (C4 (Web Text))

Max Activating Token Index: 233