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

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

Neuron 524 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: 0.8646. Min Range: -0.8646

Max Act: 0.8646. Min Act: -0.0000

Data Index: 762368 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1164308 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.8260. Min Act: 0.0000

Data Index: 560082 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.7438. Min Act: -0.0000

Data Index: 849495 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.7466. Min Act: 0.0000

Data Index: 197505 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6913. Min Act: -0.0000

Data Index: 90720 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6632. Min Act: 0.0000

Data Index: 606791 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1280577 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1121061 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6316. Min Act: -0.0000

Data Index: 830356 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6490. Min Act: 0.0000

Data Index: 1343749 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6799. Min Act: -0.0000

Data Index: 190185 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6290. Min Act: -0.0000

Data Index: 380732 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6020. Min Act: 0.0000

Data Index: 62902 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6132. Min Act: -0.0000

Data Index: 845251 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1214924 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6349. Min Act: 0.0000

Data Index: 1275120 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.5876. Min Act: -0.0000

Data Index: 869871 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.6423. Min Act: -0.0000

Data Index: 419345 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.8646. Min Range: -0.8646

Max Act: 0.5853. Min Act: -0.0000

Data Index: 167794 (C4 (Web Text))

Max Activating Token Index: 387