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

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

Neuron 3755 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.7541. Min Act: -0.0000

Data Index: 703961 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.1722. Min Act: -0.0000

Data Index: 691985 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.1210. Min Act: -0.0000

Data Index: 136136 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.1184. Min Act: -0.0000

Data Index: 917204 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.1094. Min Act: -0.0000

Data Index: 119214 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.1257. Min Act: -0.0000

Data Index: 29734 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 1.7541. Min Range: -1.7541

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1050753 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1226321 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.0985. Min Act: -0.0000

Data Index: 352438 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.0739. Min Act: -0.0000

Data Index: 425693 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.0685. Min Act: -0.0000

Data Index: 321560 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.7541. Min Range: -1.7541

Max Act: 0.9827. Min Act: -0.0000

Data Index: 993338 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.0416. Min Act: -0.0000

Data Index: 587936 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.7541. Min Range: -1.7541

Max Act: 0.9980. Min Act: -0.0000

Data Index: 62043 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.0111. Min Act: -0.0000

Data Index: 698866 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.7541. Min Range: -1.7541

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1226703 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.7541. Min Range: -1.7541

Max Act: 0.9912. Min Act: -0.0000

Data Index: 718283 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 1.7541. Min Range: -1.7541

Max Act: 0.9882. Min Act: -0.0000

Data Index: 337146 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 1.7541. Min Range: -1.7541

Max Act: 0.9574. Min Act: -0.0000

Data Index: 1110605 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 1.7541. Min Range: -1.7541

Max Act: 0.9981. Min Act: -0.0000

Data Index: 989502 (C4 (Web Text))

Max Activating Token Index: 819