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

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

Neuron 1382 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8979. Min Act: -0.0003

Data Index: 1254204 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8900. Min Act: -0.0002

Data Index: 976356 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8838. Min Act: -0.0002

Data Index: 723943 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8771. Min Act: -0.0003

Data Index: 1292704 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8746. Min Act: -0.0002

Data Index: 767632 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8476. Min Act: -0.0002

Data Index: 902582 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8684. Min Act: -0.0002

Data Index: 281271 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8347. Min Act: -0.0002

Data Index: 35526 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8251. Min Act: -0.0002

Data Index: 378761 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8443. Min Act: -0.0002

Data Index: 196294 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8139. Min Act: -0.0002

Data Index: 721422 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8178. Min Act: -0.0003

Data Index: 976364 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8056. Min Act: -0.0003

Data Index: 1198157 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8068. Min Act: -0.0003

Data Index: 835625 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8012. Min Act: -0.0002

Data Index: 836375 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8023. Min Act: -0.0003

Data Index: 910979 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7702. Min Act: -0.0003

Data Index: 563352 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7682. Min Act: -0.0003

Data Index: 32167 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7397. Min Act: -0.0002

Data Index: 875309 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7357. Min Act: -0.0003

Data Index: 602148 (C4 (Web Text))

Max Activating Token Index: 277