Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3360 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1322. Min Range: -1.1322

Max Act: 1.1322. Min Act: -0.0001

Data Index: 83871 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.1322. Min Range: -1.1322

Max Act: 1.0107. Min Act: -0.0001

Data Index: 596760 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8822. Min Act: -0.0001

Data Index: 511112 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8825. Min Act: -0.0001

Data Index: 103380 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8653. Min Act: -0.0001

Data Index: 1349925 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8611. Min Act: -0.0001

Data Index: 779574 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8339. Min Act: -0.0001

Data Index: 198838 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8261. Min Act: -0.0001

Data Index: 221476 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7810. Min Act: -0.0001

Data Index: 982602 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7661. Min Act: -0.0001

Data Index: 354199 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7951. Min Act: -0.0001

Data Index: 1347147 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8473. Min Act: -0.0001

Data Index: 184078 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8140. Min Act: -0.0001

Data Index: 1327842 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7866. Min Act: -0.0001

Data Index: 774941 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7840. Min Act: -0.0001

Data Index: 420927 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.8030. Min Act: -0.0001

Data Index: 525021 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7868. Min Act: -0.0001

Data Index: 450897 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7872. Min Act: -0.0001

Data Index: 840038 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7704. Min Act: -0.0001

Data Index: 1134080 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.1322. Min Range: -1.1322

Max Act: 0.7846. Min Act: -0.0001

Data Index: 187220 (C4 (Web Text))

Max Activating Token Index: 578