Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1753 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3880. Min Act: -0.0001

Data Index: 676305 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3514. Min Act: -0.0001

Data Index: 34383 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3748. Min Act: -0.0001

Data Index: 664468 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3542. Min Act: -0.0001

Data Index: 1357481 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3639. Min Act: -0.0001

Data Index: 418567 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3483. Min Act: -0.0001

Data Index: 414941 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3394. Min Act: -0.0001

Data Index: 1038306 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3508. Min Act: -0.0001

Data Index: 728357 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3469. Min Act: -0.0001

Data Index: 795338 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1229542 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1050069 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3115. Min Act: -0.0001

Data Index: 803120 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3224. Min Act: -0.0001

Data Index: 584286 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3214. Min Act: -0.0001

Data Index: 127175 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3307. Min Act: -0.0001

Data Index: 897116 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3201. Min Act: -0.0001

Data Index: 654063 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3061. Min Act: -0.0001

Data Index: 1046344 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3159. Min Act: -0.0001

Data Index: 893696 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3159. Min Act: -0.0001

Data Index: 280348 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.2894. Min Act: -0.0001

Data Index: 845507 (C4 (Web Text))

Max Activating Token Index: 665