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

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

Neuron 4963 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2297. Min Act: -0.0001

Data Index: 711259 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1054895 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1978. Min Act: -0.0001

Data Index: 72477 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2073. Min Act: -0.0001

Data Index: 574322 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2073. Min Act: -0.0001

Data Index: 648921 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2134. Min Act: -0.0001

Data Index: 896425 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2147. Min Act: -0.0001

Data Index: 876989 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1065699 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2092. Min Act: -0.0001

Data Index: 416954 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2032. Min Act: -0.0001

Data Index: 602682 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2024. Min Act: -0.0001

Data Index: 444937 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2071. Min Act: -0.0001

Data Index: 861597 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2052. Min Act: -0.0001

Data Index: 948591 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1305576 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1106888 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1935. Min Act: -0.0001

Data Index: 768047 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1174716 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1940. Min Act: -0.0001

Data Index: 296669 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1902. Min Act: -0.0001

Data Index: 776486 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1934. Min Act: -0.0001

Data Index: 473121 (C4 (Web Text))

Max Activating Token Index: 28