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

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

Neuron 2070 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: 0.5016. Min Range: -0.5016

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1098395 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4773. Min Act: -0.0001

Data Index: 1073958 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4893. Min Act: -0.0001

Data Index: 419243 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1209960 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1183048 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4951. Min Act: -0.0001

Data Index: 964679 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4302. Min Act: -0.0000

Data Index: 644357 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4266. Min Act: -0.0001

Data Index: 158479 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4116. Min Act: -0.0000

Data Index: 887224 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4217. Min Act: -0.0000

Data Index: 709232 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3967. Min Act: -0.0001

Data Index: 983303 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3873. Min Act: -0.0001

Data Index: 821543 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3825. Min Act: -0.0000

Data Index: 932166 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4144. Min Act: -0.0001

Data Index: 329882 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3789. Min Act: -0.0001

Data Index: 429870 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3354. Min Act: -0.0000

Data Index: 336965 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4004. Min Act: -0.0000

Data Index: 853831 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3565. Min Act: -0.0000

Data Index: 246148 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3462. Min Act: -0.0001

Data Index: 1332830 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.3771. Min Act: -0.0001

Data Index: 311821 (C4 (Web Text))

Max Activating Token Index: 172