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

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

Neuron 663 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: 0.1466. Min Range: -0.1466

Max Act: 0.1466. Min Act: -0.0000

Data Index: 321758 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1321. Min Act: -0.0000

Data Index: 957260 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1216. Min Act: -0.0001

Data Index: 937558 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1092. Min Act: -0.0001

Data Index: 824336 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1200377 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1058. Min Act: -0.0000

Data Index: 136386 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0988. Min Act: -0.0000

Data Index: 764910 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1021. Min Act: -0.0001

Data Index: 241151 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0908. Min Act: -0.0000

Data Index: 853822 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1121082 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1003. Min Act: -0.0001

Data Index: 565844 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1276079 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1274779 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0948. Min Act: -0.0001

Data Index: 320844 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1222529 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0907. Min Act: -0.0001

Data Index: 356292 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.1015. Min Act: -0.0000

Data Index: 625490 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0938. Min Act: -0.0000

Data Index: 402060 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0977. Min Act: -0.0001

Data Index: 756337 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.1466. Min Range: -0.1466

Max Act: 0.0984. Min Act: -0.0000

Data Index: 212227 (C4 (Web Text))

Max Activating Token Index: 845