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

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

Neuron 3858 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: 1.2864. Min Range: -1.2864

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1205872 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.2864. Min Act: -0.0000

Data Index: 1019415 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9753. Min Act: -0.0000

Data Index: 428009 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1211987 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1308729 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.0409. Min Act: -0.0000

Data Index: 892769 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9594. Min Act: -0.0000

Data Index: 497508 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.1080. Min Act: -0.0000

Data Index: 338873 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.0550. Min Act: -0.0000

Data Index: 642065 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.0476. Min Act: -0.0000

Data Index: 829869 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1174390 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1164070 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1455303 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9476. Min Act: -0.0000

Data Index: 440848 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9502. Min Act: -0.0000

Data Index: 105691 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9761. Min Act: -0.0000

Data Index: 731706 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1169605 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9622. Min Act: 0.0000

Data Index: 1604386 (Python Code)

Max Activating Token Index: 767

Text #18

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1272733 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9153. Min Act: -0.0000

Data Index: 205220 (C4 (Web Text))

Max Activating Token Index: 70