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

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

Neuron 3426 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.6401. Min Act: -0.0000

Data Index: 985602 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5501. Min Act: -0.0000

Data Index: 810045 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5414. Min Act: -0.0000

Data Index: 193976 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5302. Min Act: 0.0000

Data Index: 1094651 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5104. Min Act: 0.0000

Data Index: 784802 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1097375 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4934. Min Act: 0.0001

Data Index: 1268057 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.5082. Min Act: -0.0000

Data Index: 523245 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4655. Min Act: -0.0000

Data Index: 362712 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1067263 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4710. Min Act: -0.0000

Data Index: 323303 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4387. Min Act: -0.0000

Data Index: 589579 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1077819 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4339. Min Act: -0.0000

Data Index: 417686 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4310. Min Act: -0.0000

Data Index: 38851 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4203. Min Act: 0.0000

Data Index: 333039 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3986. Min Act: -0.0000

Data Index: 150301 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1250789 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4069. Min Act: 0.0000

Data Index: 1063878 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3676. Min Act: -0.0000

Data Index: 609566 (C4 (Web Text))

Max Activating Token Index: 249