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

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

Neuron 5020 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0713. Min Range: -5.0713

Max Act: 5.0713. Min Act: -0.0001

Data Index: 162810 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 5.0713. Min Range: -5.0713

Max Act: 4.5890. Min Act: -0.0001

Data Index: 1005683 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 5.0713. Min Range: -5.0713

Max Act: 4.2085. Min Act: -0.0001

Data Index: 324362 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 5.0713. Min Range: -5.0713

Max Act: 3.7294. Min Act: -0.0001

Data Index: 717974 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 5.0713. Min Range: -5.0713

Max Act: 3.8290. Min Act: -0.0001

Data Index: 508062 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 5.0713. Min Range: -5.0713

Max Act: 3.6190. Min Act: -0.0001

Data Index: 1119852 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 5.0713. Min Range: -5.0713

Max Act: 3.5558. Min Act: -0.0001

Data Index: 374961 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.9944. Min Act: -0.0001

Data Index: 1080450 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 5.0713. Min Range: -5.0713

Max Act: 3.1808. Min Act: -0.0001

Data Index: 588168 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.8326. Min Act: -0.0001

Data Index: 435954 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 5.0713. Min Range: -5.0713

Max Act: 3.0730. Min Act: -0.0001

Data Index: 518576 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.9034. Min Act: -0.0001

Data Index: 811506 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 5.0713. Min Range: -5.0713

Max Act: 3.0572. Min Act: -0.0001

Data Index: 1326699 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.8729. Min Act: -0.0001

Data Index: 1047173 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.9454. Min Act: -0.0001

Data Index: 84419 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 5.0713. Min Range: -5.0713

Max Act: 3.0666. Min Act: -0.0001

Data Index: 1130077 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.5933. Min Act: -0.0001

Data Index: 547414 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.6827. Min Act: -0.0001

Data Index: 1027820 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.7759. Min Act: -0.0001

Data Index: 541704 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 5.0713. Min Range: -5.0713

Max Act: 2.5328. Min Act: -0.0001

Data Index: 560870 (C4 (Web Text))

Max Activating Token Index: 424