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

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

Neuron 23 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1388. Min Act: -0.0001

Data Index: 351989 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1042. Min Act: -0.0001

Data Index: 143879 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1427616 (Python Code)

Max Activating Token Index: 173

Text #3

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1035. Min Act: -0.0001

Data Index: 401218 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1068. Min Act: -0.0001

Data Index: 916714 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0949. Min Act: -0.0001

Data Index: 455461 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0957. Min Act: -0.0001

Data Index: 620139 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0996. Min Act: -0.0001

Data Index: 580553 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1122980 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0994. Min Act: -0.0001

Data Index: 462495 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1297281 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1308790 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0914. Min Act: -0.0001

Data Index: 763356 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1548757 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1643421 (Python Code)

Max Activating Token Index: 399

Text #15

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0926. Min Act: -0.0001

Data Index: 53743 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1504712 (Python Code)

Max Activating Token Index: 1017

Text #17

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0917. Min Act: -0.0001

Data Index: 859564 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1488476 (Python Code)

Max Activating Token Index: 130

Text #19

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0902. Min Act: -0.0001

Data Index: 998957 (C4 (Web Text))

Max Activating Token Index: 775