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

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

Neuron 2018 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.8432. Min Act: -0.0000

Data Index: 216830 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7555. Min Act: -0.0000

Data Index: 304091 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7506. Min Act: -0.0000

Data Index: 25357 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7205. Min Act: -0.0000

Data Index: 872054 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1101529 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7071. Min Act: -0.0000

Data Index: 537182 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1087797 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1047014 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7027. Min Act: -0.0000

Data Index: 988390 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7135. Min Act: -0.0000

Data Index: 835457 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7068. Min Act: -0.0000

Data Index: 238393 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7300. Min Act: -0.0000

Data Index: 507333 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1169674 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7158. Min Act: -0.0000

Data Index: 955202 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1086163 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.6676. Min Act: -0.0000

Data Index: 4369 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.6922. Min Act: -0.0000

Data Index: 832215 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.6852. Min Act: -0.0000

Data Index: 187320 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.6847. Min Act: -0.0000

Data Index: 931384 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1356705 (C4 (Web Text))

Max Activating Token Index: 985