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

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

Neuron 4000 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: 0.5848. Min Range: -0.5848

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1187035 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.5338. Min Act: -0.0000

Data Index: 861494 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1120625 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1082113 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4856. Min Act: 0.0000

Data Index: 956092 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1321423 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1258166 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1134948 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1343489 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4051. Min Act: 0.0002

Data Index: 434007 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1304223 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4071. Min Act: 0.0000

Data Index: 796510 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1311624 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3964. Min Act: -0.0000

Data Index: 819096 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3980. Min Act: -0.0000

Data Index: 360401 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4155. Min Act: -0.0000

Data Index: 882946 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1329908 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3641. Min Act: -0.0000

Data Index: 634684 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3693. Min Act: -0.0000

Data Index: 462415 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.5848. Min Range: -0.5848

Max Act: 0.3832. Min Act: 0.0000

Data Index: 1195806 (C4 (Web Text))

Max Activating Token Index: 681