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

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

Neuron 1322 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: 1.6951. Min Range: -1.6951

Max Act: 1.6951. Min Act: -0.0001

Data Index: 225696 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.4525. Min Act: -0.0002

Data Index: 1280782 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5285. Min Act: -0.0002

Data Index: 736202 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.6437. Min Act: -0.0002

Data Index: 679369 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5377. Min Act: -0.0002

Data Index: 138500 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5769. Min Act: -0.0002

Data Index: 738681 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5363. Min Act: -0.0001

Data Index: 476838 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5930. Min Act: -0.0001

Data Index: 82304 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3926. Min Act: -0.0001

Data Index: 595827 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5569. Min Act: -0.0002

Data Index: 167448 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.4232. Min Act: -0.0001

Data Index: 758956 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.4165. Min Act: -0.0002

Data Index: 208992 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3948. Min Act: -0.0001

Data Index: 1063619 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3629. Min Act: -0.0002

Data Index: 1158557 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.4386. Min Act: -0.0001

Data Index: 365217 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3029. Min Act: -0.0002

Data Index: 1089860 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3543. Min Act: -0.0002

Data Index: 236432 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3559. Min Act: -0.0002

Data Index: 1038655 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3007. Min Act: -0.0002

Data Index: 962669 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3855. Min Act: -0.0001

Data Index: 1118721 (C4 (Web Text))

Max Activating Token Index: 975