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

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

Neuron 4205 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: 3.7917. Min Range: -3.7917

Max Act: 3.7917. Min Act: -0.0001

Data Index: 1174943 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.4212. Min Act: -0.0001

Data Index: 607008 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.2738. Min Act: -0.0001

Data Index: 781350 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.2665. Min Act: -0.0001

Data Index: 634975 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.3144. Min Act: -0.0001

Data Index: 869127 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.4944. Min Act: -0.0001

Data Index: 244133 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.0562. Min Act: -0.0001

Data Index: 1347337 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 3.7917. Min Range: -3.7917

Max Act: 3.0102. Min Act: -0.0001

Data Index: 707800 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.9757. Min Act: -0.0001

Data Index: 1094244 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.8048. Min Act: -0.0001

Data Index: 1188861 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.8617. Min Act: -0.0001

Data Index: 146079 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.5995. Min Act: -0.0001

Data Index: 1152325 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.7024. Min Act: -0.0001

Data Index: 1135272 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.7034. Min Act: -0.0001

Data Index: 878552 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.8131. Min Act: -0.0001

Data Index: 1017286 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.6427. Min Act: -0.0001

Data Index: 475749 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.7335. Min Act: -0.0001

Data Index: 1328984 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.5668. Min Act: -0.0001

Data Index: 896028 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.5101. Min Act: -0.0001

Data Index: 999349 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 3.7917. Min Range: -3.7917

Max Act: 2.4458. Min Act: -0.0001

Data Index: 1359195 (C4 (Web Text))

Max Activating Token Index: 229