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

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

Neuron 2151 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.1768. Min Act: -0.0000

Data Index: 925924 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.1910. Min Act: -0.0000

Data Index: 772024 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.2283. Min Act: -0.0000

Data Index: 462777 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1168008 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1205928 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.1256. Min Act: -0.0000

Data Index: 152926 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.0849. Min Act: -0.0000

Data Index: 122736 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.0438. Min Act: -0.0000

Data Index: 299098 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.0322. Min Act: -0.0000

Data Index: 808390 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.2283. Min Range: -1.2283

Max Act: 0.9984. Min Act: -0.0000

Data Index: 352329 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.0899. Min Act: -0.0000

Data Index: 131840 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.2283. Min Range: -1.2283

Max Act: 0.9757. Min Act: -0.0000

Data Index: 457685 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 1.2283. Min Range: -1.2283

Max Act: 0.9739. Min Act: -0.0000

Data Index: 531874 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 1.2283. Min Range: -1.2283

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1080826 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 1.2283. Min Range: -1.2283

Max Act: 0.9497. Min Act: -0.0000

Data Index: 363187 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1121751 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.2283. Min Range: -1.2283

Max Act: 0.9878. Min Act: -0.0001

Data Index: 442189 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.2283. Min Range: -1.2283

Max Act: 0.9672. Min Act: -0.0000

Data Index: 822037 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.2283. Min Range: -1.2283

Max Act: 1.0079. Min Act: -0.0000

Data Index: 268707 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 1.2283. Min Range: -1.2283

Max Act: 0.9307. Min Act: -0.0001

Data Index: 649203 (C4 (Web Text))

Max Activating Token Index: 1010