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

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

Neuron 427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9054. Min Act: -0.0000

Data Index: 365335 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9357. Min Act: -0.0000

Data Index: 561509 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9365. Min Act: -0.0000

Data Index: 538951 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8350. Min Act: -0.0000

Data Index: 88303 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7736. Min Act: -0.0000

Data Index: 84036 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7349. Min Act: -0.0000

Data Index: 114908 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7509. Min Act: -0.0000

Data Index: 760150 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6898. Min Act: -0.0000

Data Index: 557326 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6585. Min Act: -0.0000

Data Index: 90656 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1135121 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1229286 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1252738 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6350. Min Act: -0.0000

Data Index: 35531 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6529. Min Act: -0.0000

Data Index: 654421 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6477. Min Act: -0.0000

Data Index: 775752 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1257589 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.5927. Min Act: -0.0000

Data Index: 470256 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6254. Min Act: -0.0000

Data Index: 310434 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6208. Min Act: -0.0000

Data Index: 648651 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6001. Min Act: -0.0000

Data Index: 603263 (C4 (Web Text))

Max Activating Token Index: 109