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

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

Neuron 814 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1325050 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8086. Min Act: -0.0000

Data Index: 600515 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1045731 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7189. Min Act: -0.0000

Data Index: 456451 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7077. Min Act: -0.0000

Data Index: 330709 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1044668 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6821. Min Act: -0.0000

Data Index: 371542 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1305947 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6086. Min Act: -0.0000

Data Index: 264927 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1246310 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5966. Min Act: -0.0000

Data Index: 881748 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1187932 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6100. Min Act: -0.0000

Data Index: 267736 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1021284 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5558. Min Act: -0.0000

Data Index: 480308 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5945. Min Act: -0.0000

Data Index: 270539 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5370. Min Act: -0.0000

Data Index: 762768 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1339623 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1114358 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5257. Min Act: -0.0000

Data Index: 941860 (C4 (Web Text))

Max Activating Token Index: 845