Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3165 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1170994 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.8831. Min Act: -0.0001

Data Index: 27591 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7791. Min Act: -0.0001

Data Index: 1072710 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.8440. Min Act: -0.0001

Data Index: 930730 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7658. Min Act: -0.0001

Data Index: 782618 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7707. Min Act: -0.0001

Data Index: 268171 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6747. Min Act: -0.0001

Data Index: 646571 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6708. Min Act: -0.0001

Data Index: 901731 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7079. Min Act: -0.0001

Data Index: 884845 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7210. Min Act: -0.0001

Data Index: 375548 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6884. Min Act: -0.0001

Data Index: 1090208 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6793. Min Act: -0.0001

Data Index: 972483 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7119. Min Act: -0.0001

Data Index: 1504090 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6966. Min Act: -0.0001

Data Index: 415999 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6303. Min Act: -0.0001

Data Index: 793925 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6090. Min Act: -0.0001

Data Index: 1154660 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.5679. Min Act: -0.0001

Data Index: 395928 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6426. Min Act: -0.0001

Data Index: 1543147 (Python Code)

Max Activating Token Index: 681

Text #18

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6404. Min Act: -0.0001

Data Index: 893653 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6176. Min Act: -0.0001

Data Index: 809360 (C4 (Web Text))

Max Activating Token Index: 885