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

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

Neuron 2162 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0649. Min Range: -3.0649

Max Act: 3.0649. Min Act: -0.0000

Data Index: 1356519 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.8968. Min Act: -0.0000

Data Index: 236948 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.5866. Min Act: -0.0000

Data Index: 641151 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.6422. Min Act: -0.0000

Data Index: 1083169 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.6257. Min Act: -0.0001

Data Index: 805139 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.5634. Min Act: -0.0001

Data Index: 682907 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.5798. Min Act: -0.0000

Data Index: 175639 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.4250. Min Act: 0.0000

Data Index: 417110 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.5531. Min Act: -0.0001

Data Index: 328872 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.4291. Min Act: -0.0000

Data Index: 914370 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.3958. Min Act: -0.0001

Data Index: 835708 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.3137. Min Act: 0.0000

Data Index: 438517 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.3040. Min Act: -0.0001

Data Index: 207639 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.1758. Min Act: -0.0000

Data Index: 171879 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.3220. Min Act: -0.0001

Data Index: 1051091 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.2602. Min Act: -0.0001

Data Index: 58886 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.3309. Min Act: -0.0000

Data Index: 162777 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.3886. Min Act: -0.0001

Data Index: 1297690 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.2425. Min Act: -0.0000

Data Index: 276891 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 3.0649. Min Range: -3.0649

Max Act: 2.3022. Min Act: -0.0000

Data Index: 291350 (C4 (Web Text))

Max Activating Token Index: 825