Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 672 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0286. Min Act: -0.0006

Data Index: 841710 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0258. Min Act: -0.0006

Data Index: 439258 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0260. Min Act: -0.0006

Data Index: 696959 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0257. Min Act: -0.0006

Data Index: 631940 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1112562 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1099773 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0248. Min Act: -0.0006

Data Index: 195813 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0258. Min Act: -0.0006

Data Index: 584701 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1206941 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0245. Min Act: -0.0006

Data Index: 413731 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1111765 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0245. Min Act: -0.0006

Data Index: 656484 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1035407 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0249. Min Act: -0.0006

Data Index: 746439 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1077860 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0242. Min Act: -0.0006

Data Index: 597228 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1292004 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0247. Min Act: -0.0006

Data Index: 488978 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0247. Min Act: -0.0006

Data Index: 583956 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1322695 (C4 (Web Text))

Max Activating Token Index: 712