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

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

Neuron 507 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5193. Min Range: -2.5193

Max Act: 2.4034. Min Act: -0.0000

Data Index: 1178375 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 2.5193. Min Range: -2.5193

Max Act: 2.0754. Min Act: -0.0000

Data Index: 383315 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 2.5193. Min Range: -2.5193

Max Act: 2.2935. Min Act: -0.0000

Data Index: 421217 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.9470. Min Act: -0.0000

Data Index: 1293449 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 2.5193. Min Range: -2.5193

Max Act: 2.5193. Min Act: -0.0000

Data Index: 1163178 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 2.5193. Min Range: -2.5193

Max Act: 2.1470. Min Act: -0.0000

Data Index: 835294 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.9604. Min Act: -0.0000

Data Index: 439525 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.8306. Min Act: -0.0000

Data Index: 602258 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.5968. Min Act: -0.0000

Data Index: 783174 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.5012. Min Act: -0.0000

Data Index: 387048 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.7641. Min Act: -0.0000

Data Index: 763218 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.7896. Min Act: -0.0000

Data Index: 783112 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.7930. Min Act: -0.0000

Data Index: 1007516 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.7690. Min Act: -0.0000

Data Index: 1322621 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.8061. Min Act: -0.0000

Data Index: 980303 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.8766. Min Act: -0.0000

Data Index: 548060 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.6078. Min Act: -0.0000

Data Index: 848841 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.6075. Min Act: -0.0000

Data Index: 479027 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.6167. Min Act: -0.0000

Data Index: 1068266 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 2.5193. Min Range: -2.5193

Max Act: 1.5909. Min Act: -0.0000

Data Index: 55617 (C4 (Web Text))

Max Activating Token Index: 377