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

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

Neuron 654 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5863. Min Act: -0.0002

Data Index: 567344 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5819. Min Act: -0.0002

Data Index: 277228 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5597. Min Act: -0.0002

Data Index: 866063 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5497. Min Act: -0.0002

Data Index: 817285 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5447. Min Act: -0.0002

Data Index: 995278 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5420. Min Act: -0.0002

Data Index: 295334 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5434. Min Act: -0.0002

Data Index: 22566 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5354. Min Act: -0.0002

Data Index: 60039 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5221. Min Act: -0.0002

Data Index: 334396 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5617. Min Act: -0.0002

Data Index: 1184429 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5427. Min Act: -0.0002

Data Index: 82670 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5439. Min Act: -0.0002

Data Index: 777329 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5595. Min Act: -0.0002

Data Index: 647864 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5081. Min Act: -0.0002

Data Index: 564300 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5872. Min Act: -0.0002

Data Index: 1162848 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5172. Min Act: -0.0002

Data Index: 95768 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5117. Min Act: -0.0002

Data Index: 1198548 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5102. Min Act: -0.0002

Data Index: 1289264 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5035. Min Act: -0.0002

Data Index: 384155 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.5872. Min Range: -0.5872

Max Act: 0.5228. Min Act: -0.0002

Data Index: 243027 (C4 (Web Text))

Max Activating Token Index: 120