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

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

Neuron 4616 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3580. Min Range: -1.3580

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1089501 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 1.3580. Min Range: -1.3580

Max Act: 1.1875. Min Act: -0.0000

Data Index: 862393 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1179547 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.8227. Min Act: -0.0000

Data Index: 189105 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.7336. Min Act: -0.0000

Data Index: 602047 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.7678. Min Act: -0.0000

Data Index: 913567 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6757. Min Act: -0.0000

Data Index: 42647 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6964. Min Act: -0.0000

Data Index: 590641 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1186890 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6664. Min Act: -0.0000

Data Index: 341849 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6691. Min Act: -0.0000

Data Index: 880850 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1090890 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6054. Min Act: -0.0000

Data Index: 376966 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5731. Min Act: -0.0000

Data Index: 297076 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5808. Min Act: -0.0000

Data Index: 898680 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5904. Min Act: -0.0000

Data Index: 559026 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1024538 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1143208 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1024984 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5464. Min Act: -0.0000

Data Index: 371755 (C4 (Web Text))

Max Activating Token Index: 39