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

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

Neuron 3300 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1911. Min Range: -3.1911

Max Act: 3.1911. Min Act: -0.0001

Data Index: 1192125 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.9182. Min Act: -0.0001

Data Index: 1248102 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.8474. Min Act: -0.0001

Data Index: 859359 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.6953. Min Act: -0.0001

Data Index: 723531 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.6283. Min Act: -0.0001

Data Index: 131231 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.6209. Min Act: -0.0001

Data Index: 812820 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.6010. Min Act: -0.0001

Data Index: 295038 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.6012. Min Act: -0.0001

Data Index: 211115 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5765. Min Act: -0.0001

Data Index: 453999 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5646. Min Act: -0.0001

Data Index: 70320 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5747. Min Act: -0.0001

Data Index: 449941 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5550. Min Act: -0.0001

Data Index: 759991 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.6902. Min Act: -0.0001

Data Index: 48857 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5573. Min Act: -0.0001

Data Index: 93772 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5488. Min Act: -0.0001

Data Index: 319141 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5329. Min Act: -0.0001

Data Index: 1015606 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.4226. Min Act: -0.0001

Data Index: 620884 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5387. Min Act: -0.0001

Data Index: 1225818 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5289. Min Act: -0.0001

Data Index: 1041468 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.1911. Min Range: -3.1911

Max Act: 2.5376. Min Act: -0.0001

Data Index: 939291 (C4 (Web Text))

Max Activating Token Index: 11