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

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

Neuron 4709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3745. Min Range: -2.3745

Max Act: 2.2555. Min Act: -0.0000

Data Index: 982626 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 2.3745. Min Range: -2.3745

Max Act: 2.3745. Min Act: -0.0000

Data Index: 272169 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 2.3745. Min Range: -2.3745

Max Act: 2.3668. Min Act: -0.0000

Data Index: 639996 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 2.3745. Min Range: -2.3745

Max Act: 2.3367. Min Act: -0.0000

Data Index: 163594 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 2.3745. Min Range: -2.3745

Max Act: 2.1300. Min Act: -0.0000

Data Index: 847236 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 2.3745. Min Range: -2.3745

Max Act: 2.0335. Min Act: -0.0000

Data Index: 393493 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.9104. Min Act: -0.0000

Data Index: 1151354 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 2.3745. Min Range: -2.3745

Max Act: 2.0316. Min Act: -0.0000

Data Index: 982114 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 2.3745. Min Range: -2.3745

Max Act: 2.0127. Min Act: -0.0000

Data Index: 1238698 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.9840. Min Act: -0.0000

Data Index: 1114184 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.9670. Min Act: -0.0000

Data Index: 814838 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.8641. Min Act: -0.0000

Data Index: 1269385 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.8221. Min Act: -0.0000

Data Index: 407443 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1322474 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.7886. Min Act: -0.0000

Data Index: 949279 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.7672. Min Act: -0.0000

Data Index: 194463 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.7704. Min Act: -0.0000

Data Index: 1154668 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.7545. Min Act: -0.0000

Data Index: 678639 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.7340. Min Act: -0.0000

Data Index: 75557 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 2.3745. Min Range: -2.3745

Max Act: 1.5717. Min Act: -0.0000

Data Index: 1271378 (C4 (Web Text))

Max Activating Token Index: 362