Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 574 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5960. Min Act: -0.0002

Data Index: 938584 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5780. Min Act: -0.0001

Data Index: 378309 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5745. Min Act: -0.0001

Data Index: 1523202 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5365. Min Act: -0.0002

Data Index: 913019 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5408. Min Act: -0.0001

Data Index: 1038047 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5304. Min Act: -0.0001

Data Index: 171876 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5314. Min Act: -0.0001

Data Index: 32276 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4963. Min Act: -0.0001

Data Index: 1275746 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5289. Min Act: -0.0001

Data Index: 645813 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5429. Min Act: -0.0001

Data Index: 827956 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5434. Min Act: -0.0001

Data Index: 145952 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5413. Min Act: -0.0001

Data Index: 1004067 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5284. Min Act: -0.0001

Data Index: 657408 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5378. Min Act: -0.0001

Data Index: 960817 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5379. Min Act: -0.0001

Data Index: 811262 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5204. Min Act: -0.0001

Data Index: 956930 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5247. Min Act: -0.0002

Data Index: 773232 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5184. Min Act: -0.0002

Data Index: 359208 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5039. Min Act: -0.0001

Data Index: 506933 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5020. Min Act: -0.0001

Data Index: 539389 (C4 (Web Text))

Max Activating Token Index: 169