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

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

Neuron 621 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2489. Min Range: -1.2489

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1219772 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 1.2489. Min Range: -1.2489

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1023878 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 1.2489. Min Range: -1.2489

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1204556 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.2489. Min Range: -1.2489

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1322526 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 1.2489. Min Range: -1.2489

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1324711 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.2489. Min Range: -1.2489

Max Act: 1.0276. Min Act: -0.0000

Data Index: 431112 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 1.2489. Min Range: -1.2489

Max Act: 1.0258. Min Act: -0.0000

Data Index: 701955 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.2489. Min Range: -1.2489

Max Act: 1.0782. Min Act: -0.0000

Data Index: 550876 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.9752. Min Act: -0.0000

Data Index: 189923 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1229712 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1255237 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.9416. Min Act: -0.0000

Data Index: 685175 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.8427. Min Act: -0.0000

Data Index: 628673 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.8994. Min Act: -0.0000

Data Index: 197544 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.8385. Min Act: -0.0000

Data Index: 822646 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.8606. Min Act: -0.0000

Data Index: 132831 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.8252. Min Act: -0.0000

Data Index: 470826 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.9226. Min Act: -0.0000

Data Index: 438676 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.8324. Min Act: -0.0000

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.2489. Min Range: -1.2489

Max Act: 0.8352. Min Act: -0.0000

Data Index: 533930 (C4 (Web Text))

Max Activating Token Index: 879