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

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

Neuron 4503 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: 0.1361. Min Range: -0.1361

Max Act: 0.1244. Min Act: -0.0002

Data Index: 829473 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0002

Data Index: 1073211 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1205170 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0983. Min Act: -0.0002

Data Index: 790640 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0968. Min Act: -0.0002

Data Index: 301911 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1050. Min Act: -0.0002

Data Index: 19614 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0932. Min Act: -0.0002

Data Index: 566995 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1167613 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1220965 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1317505 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0975. Min Act: -0.0002

Data Index: 382059 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1034. Min Act: -0.0002

Data Index: 147352 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1020. Min Act: -0.0002

Data Index: 811764 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0954. Min Act: -0.0002

Data Index: 291395 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0942. Min Act: -0.0002

Data Index: 826309 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1023986 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1204144 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0983. Min Act: -0.0002

Data Index: 866883 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0962. Min Act: -0.0002

Data Index: 586329 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1256788 (C4 (Web Text))

Max Activating Token Index: 624