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

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

Neuron 2759 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4067. Min Act: -0.0001

Data Index: 903788 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4333. Min Act: -0.0001

Data Index: 1399794 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4138. Min Act: -0.0002

Data Index: 129480 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4238. Min Act: -0.0001

Data Index: 1310955 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4171. Min Act: -0.0001

Data Index: 623658 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4245. Min Act: -0.0001

Data Index: 1158839 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3951. Min Act: -0.0001

Data Index: 1281713 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4143. Min Act: -0.0001

Data Index: 263330 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4119. Min Act: -0.0001

Data Index: 42410 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.4002. Min Act: -0.0001

Data Index: 658256 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3994. Min Act: -0.0001

Data Index: 1039118 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3810. Min Act: -0.0001

Data Index: 1316334 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3921. Min Act: -0.0001

Data Index: 166259 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3901. Min Act: -0.0001

Data Index: 763868 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3847. Min Act: -0.0002

Data Index: 1070751 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3749. Min Act: -0.0002

Data Index: 219423 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3782. Min Act: -0.0001

Data Index: 1350341 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3764. Min Act: -0.0001

Data Index: 508049 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3953. Min Act: -0.0001

Data Index: 287909 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.4333. Min Range: -0.4333

Max Act: 0.3492. Min Act: -0.0002

Data Index: 866557 (C4 (Web Text))

Max Activating Token Index: 968