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

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

Neuron 1080 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: 0.5306. Min Range: -0.5306

Max Act: 0.5306. Min Act: -0.0001

Data Index: 863106 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.5153. Min Act: -0.0001

Data Index: 770725 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1012755 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.5007. Min Act: -0.0000

Data Index: 655787 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4849. Min Act: -0.0001

Data Index: 809248 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1172875 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4570. Min Act: -0.0001

Data Index: 1294717 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4675. Min Act: -0.0001

Data Index: 699314 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4614. Min Act: -0.0001

Data Index: 1086665 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4734. Min Act: -0.0001

Data Index: 1205447 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4576. Min Act: -0.0000

Data Index: 428626 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4681. Min Act: -0.0000

Data Index: 68384 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4389. Min Act: -0.0001

Data Index: 1138615 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4181. Min Act: -0.0000

Data Index: 99962 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4335. Min Act: -0.0001

Data Index: 1335455 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4286. Min Act: 0.0000

Data Index: 999884 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4166. Min Act: -0.0001

Data Index: 1047306 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4101. Min Act: -0.0000

Data Index: 406767 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1017674 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4043. Min Act: -0.0000

Data Index: 953872 (C4 (Web Text))

Max Activating Token Index: 892