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

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

Neuron 2837 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: 1.0802. Min Range: -1.0802

Max Act: 1.0802. Min Act: -0.0000

Data Index: 485250 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9833. Min Act: -0.0000

Data Index: 130916 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1238455 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9555. Min Act: -0.0000

Data Index: 540901 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9197. Min Act: -0.0000

Data Index: 680907 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7861. Min Act: -0.0000

Data Index: 856555 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.6938. Min Act: -0.0000

Data Index: 66300 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8128. Min Act: -0.0000

Data Index: 875881 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7749. Min Act: -0.0000

Data Index: 236145 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1348617 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1214265 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8062. Min Act: -0.0000

Data Index: 670579 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1195950 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7019. Min Act: -0.0000

Data Index: 907565 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7432. Min Act: -0.0000

Data Index: 522905 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.6685. Min Act: -0.0000

Data Index: 722356 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7017. Min Act: -0.0000

Data Index: 714069 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.6796. Min Act: -0.0000

Data Index: 823367 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1065492 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.6608. Min Act: -0.0000

Data Index: 753696 (C4 (Web Text))

Max Activating Token Index: 771