Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 230 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.9587. Min Act: -0.0002

Data Index: 150890 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.9011. Min Act: -0.0002

Data Index: 1328852 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8618. Min Act: -0.0002

Data Index: 1136453 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8291. Min Act: -0.0002

Data Index: 1175931 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8478. Min Act: -0.0002

Data Index: 567628 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7897. Min Act: -0.0002

Data Index: 509125 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8977. Min Act: -0.0002

Data Index: 885246 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7852. Min Act: -0.0002

Data Index: 31553 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8353. Min Act: -0.0002

Data Index: 724150 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8462. Min Act: -0.0002

Data Index: 1032767 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8378. Min Act: -0.0002

Data Index: 75568 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7781. Min Act: -0.0002

Data Index: 235243 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7696. Min Act: -0.0002

Data Index: 1181486 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6721. Min Act: -0.0002

Data Index: 795252 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7426. Min Act: -0.0001

Data Index: 213225 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7804. Min Act: -0.0002

Data Index: 1353529 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8093. Min Act: -0.0002

Data Index: 879594 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8399. Min Act: -0.0001

Data Index: 769298 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7350. Min Act: -0.0001

Data Index: 583078 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7945. Min Act: -0.0002

Data Index: 332185 (C4 (Web Text))

Max Activating Token Index: 716