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

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

Neuron 1866 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: 0.6764. Min Range: -0.6764

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1129888 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5790. Min Act: -0.0000

Data Index: 799294 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.6091. Min Act: -0.0000

Data Index: 99457 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5767. Min Act: -0.0000

Data Index: 56302 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5433. Min Act: -0.0000

Data Index: 717168 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1340686 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5365. Min Act: -0.0000

Data Index: 853965 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1334977 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5054. Min Act: -0.0000

Data Index: 799470 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5224. Min Act: -0.0000

Data Index: 896057 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5019. Min Act: -0.0000

Data Index: 660531 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4980. Min Act: -0.0000

Data Index: 25568 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4677. Min Act: -0.0000

Data Index: 742255 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1018462 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4978. Min Act: -0.0000

Data Index: 245750 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.5059. Min Act: -0.0000

Data Index: 148473 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4751. Min Act: -0.0000

Data Index: 473778 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1289617 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4613. Min Act: -0.0000

Data Index: 963554 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.6764. Min Range: -0.6764

Max Act: 0.4603. Min Act: -0.0000

Data Index: 303244 (C4 (Web Text))

Max Activating Token Index: 979