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

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

Neuron 904 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1133760 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.2037. Min Range: -1.2037

Max Act: 1.0268. Min Act: -0.0000

Data Index: 713535 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1054447 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9818. Min Act: -0.0000

Data Index: 744820 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9237. Min Act: -0.0000

Data Index: 929021 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.9266. Min Act: -0.0000

Data Index: 712863 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8967. Min Act: -0.0000

Data Index: 655616 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8665. Min Act: -0.0000

Data Index: 615280 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8362. Min Act: -0.0001

Data Index: 787421 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1009180 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8038. Min Act: -0.0001

Data Index: 293195 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.7432. Min Act: -0.0001

Data Index: 1214790 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8494. Min Act: -0.0001

Data Index: 993246 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8038. Min Act: -0.0001

Data Index: 1129592 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8165. Min Act: -0.0001

Data Index: 472208 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.7895. Min Act: -0.0001

Data Index: 170620 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1038615 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8005. Min Act: -0.0001

Data Index: 683873 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8717. Min Act: -0.0001

Data Index: 628135 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.2037. Min Range: -1.2037

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1171944 (C4 (Web Text))

Max Activating Token Index: 141