Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1681 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9145. Min Range: -2.9145

Max Act: 2.9145. Min Act: -0.0000

Data Index: 823780 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 2.9145. Min Range: -2.9145

Max Act: 2.3065. Min Act: -0.0000

Data Index: 727669 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 2.9145. Min Range: -2.9145

Max Act: 2.2377. Min Act: -0.0000

Data Index: 23058 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.7769. Min Act: -0.0000

Data Index: 443883 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 2.9145. Min Range: -2.9145

Max Act: 2.0742. Min Act: -0.0000

Data Index: 896290 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 2.9145. Min Range: -2.9145

Max Act: 2.1696. Min Act: -0.0000

Data Index: 1282695 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 2.9145. Min Range: -2.9145

Max Act: 2.0098. Min Act: -0.0000

Data Index: 853421 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 2.9145. Min Range: -2.9145

Max Act: 2.0031. Min Act: -0.0000

Data Index: 114646 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.9489. Min Act: -0.0000

Data Index: 166909 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 2.9145. Min Range: -2.9145

Max Act: 2.0126. Min Act: -0.0000

Data Index: 720177 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.8704. Min Act: -0.0000

Data Index: 1307399 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.8669. Min Act: -0.0000

Data Index: 177999 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.6707. Min Act: -0.0000

Data Index: 375710 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.7891. Min Act: -0.0000

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.8643. Min Act: -0.0000

Data Index: 1383612 (Python Code)

Max Activating Token Index: 314

Text #15

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.9494. Min Act: -0.0000

Data Index: 1347885 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.7394. Min Act: -0.0000

Data Index: 1045691 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.8388. Min Act: -0.0000

Data Index: 181859 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.7214. Min Act: -0.0000

Data Index: 1591775 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 2.9145. Min Range: -2.9145

Max Act: 1.7889. Min Act: -0.0000

Data Index: 1001877 (C4 (Web Text))

Max Activating Token Index: 485