Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3028 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2181. Min Range: -2.2181

Max Act: 2.2181. Min Act: -0.0002

Data Index: 66479 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 2.2181. Min Range: -2.2181

Max Act: 2.1389. Min Act: -0.0002

Data Index: 416004 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.9699. Min Act: -0.0002

Data Index: 387730 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7934. Min Act: -0.0002

Data Index: 580164 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.8194. Min Act: -0.0002

Data Index: 303339 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.8753. Min Act: -0.0002

Data Index: 335837 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7671. Min Act: -0.0002

Data Index: 327018 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.8600. Min Act: -0.0002

Data Index: 1326633 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7917. Min Act: -0.0002

Data Index: 641757 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.8370. Min Act: -0.0002

Data Index: 824988 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7831. Min Act: -0.0002

Data Index: 1225778 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7668. Min Act: -0.0002

Data Index: 1338786 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7170. Min Act: -0.0002

Data Index: 936943 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7557. Min Act: -0.0002

Data Index: 835129 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7179. Min Act: -0.0002

Data Index: 983791 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7082. Min Act: -0.0002

Data Index: 1249706 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.6568. Min Act: -0.0002

Data Index: 1096782 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7363. Min Act: -0.0002

Data Index: 1245489 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.6741. Min Act: -0.0002

Data Index: 623173 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.6253. Min Act: -0.0002

Data Index: 1067700 (C4 (Web Text))

Max Activating Token Index: 333