Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3446 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5844. Min Act: -0.0000

Data Index: 940471 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5867. Min Act: -0.0000

Data Index: 295542 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.6225. Min Act: -0.0000

Data Index: 278946 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5767. Min Act: -0.0000

Data Index: 943764 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5191. Min Act: -0.0000

Data Index: 824755 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4945. Min Act: -0.0000

Data Index: 51106 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5850. Min Act: -0.0000

Data Index: 93385 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5365. Min Act: -0.0000

Data Index: 467252 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1224163 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5618. Min Act: -0.0000

Data Index: 450045 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5105. Min Act: -0.0000

Data Index: 122620 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1069364 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5229. Min Act: -0.0000

Data Index: 83968 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5364. Min Act: -0.0000

Data Index: 299553 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1487952 (Python Code)

Max Activating Token Index: 520

Text #15

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1298166 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4844. Min Act: -0.0000

Data Index: 344135 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1504664 (Python Code)

Max Activating Token Index: 748

Text #18

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5487. Min Act: -0.0000

Data Index: 357767 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.6225. Min Range: -0.6225

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1397947 (Python Code)

Max Activating Token Index: 697