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

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

Neuron 4142 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.8580. Min Act: -0.0000

Data Index: 269306 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.8475. Min Act: -0.0000

Data Index: 560421 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1120707 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7911. Min Act: -0.0000

Data Index: 712217 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.8122. Min Act: -0.0000

Data Index: 382462 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7899. Min Act: -0.0000

Data Index: 495095 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7890. Min Act: -0.0000

Data Index: 424616 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1011266 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1231874 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7182. Min Act: -0.0000

Data Index: 930053 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7226. Min Act: -0.0000

Data Index: 205510 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7100. Min Act: -0.0000

Data Index: 192138 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7438. Min Act: -0.0000

Data Index: 713565 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7029. Min Act: -0.0000

Data Index: 417388 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7187. Min Act: -0.0000

Data Index: 474680 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6529. Min Act: -0.0000

Data Index: 523984 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6900. Min Act: -0.0000

Data Index: 196761 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7071. Min Act: -0.0000

Data Index: 836311 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6112. Min Act: 0.0001

Data Index: 1196912 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6598. Min Act: -0.0000

Data Index: 81759 (C4 (Web Text))

Max Activating Token Index: 859