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

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

Neuron 66 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.6523. Min Act: -0.0002

Data Index: 959364 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 3.6523. Min Range: -3.6523

Max Act: 2.1785. Min Act: -0.0002

Data Index: 1117723 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.6586. Min Act: -0.0002

Data Index: 1321639 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.6854. Min Act: -0.0002

Data Index: 823275 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.6631. Min Act: -0.0002

Data Index: 1039546 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.5403. Min Act: -0.0002

Data Index: 1169321 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.4258. Min Act: -0.0002

Data Index: 582453 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.3278. Min Act: -0.0002

Data Index: 151343 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.4616. Min Act: -0.0002

Data Index: 832441 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.4192. Min Act: -0.0002

Data Index: 1148779 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.3906. Min Act: -0.0002

Data Index: 355644 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.4479. Min Act: -0.0002

Data Index: 188057 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.3351. Min Act: -0.0002

Data Index: 269024 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.4435. Min Act: -0.0002

Data Index: 1001897 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.2531. Min Act: -0.0002

Data Index: 1104411 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.3441. Min Act: -0.0002

Data Index: 1253249 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.4703. Min Act: -0.0002

Data Index: 157799 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.4220. Min Act: -0.0002

Data Index: 843686 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.4224. Min Act: -0.0002

Data Index: 122964 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 3.6523. Min Range: -3.6523

Max Act: 1.3662. Min Act: -0.0002

Data Index: 599597 (C4 (Web Text))

Max Activating Token Index: 250