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

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

Neuron 2852 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: 0.7987. Min Range: -0.7987

Max Act: 0.7987. Min Act: -0.0001

Data Index: 772999 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6855. Min Act: -0.0001

Data Index: 513331 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5866. Min Act: -0.0001

Data Index: 1022687 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.6024. Min Act: -0.0001

Data Index: 1290965 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5700. Min Act: -0.0001

Data Index: 555220 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5343. Min Act: -0.0001

Data Index: 1041566 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5450. Min Act: -0.0001

Data Index: 439314 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5393. Min Act: -0.0001

Data Index: 259656 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5093. Min Act: -0.0001

Data Index: 907372 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5014. Min Act: -0.0001

Data Index: 29331 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5161. Min Act: -0.0001

Data Index: 1134524 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5190. Min Act: -0.0001

Data Index: 1178808 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5021. Min Act: -0.0001

Data Index: 365840 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.4905. Min Act: -0.0001

Data Index: 750196 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.4749. Min Act: -0.0001

Data Index: 10166 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.4711. Min Act: -0.0001

Data Index: 47982 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.4521. Min Act: -0.0001

Data Index: 396014 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.5241. Min Act: -0.0001

Data Index: 452702 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.4730. Min Act: -0.0001

Data Index: 426589 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.7987. Min Range: -0.7987

Max Act: 0.4414. Min Act: -0.0001

Data Index: 679454 (C4 (Web Text))

Max Activating Token Index: 1011