Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2241 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.2891. Min Act: -0.0002

Data Index: 441075 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.2149. Min Act: -0.0002

Data Index: 484990 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1026. Min Act: -0.0002

Data Index: 972265 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.1094. Min Act: -0.0002

Data Index: 1321667 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0402. Min Act: -0.0002

Data Index: 1178277 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 1.2891. Min Range: -1.2891

Max Act: 1.0745. Min Act: -0.0002

Data Index: 1335597 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.9594. Min Act: -0.0002

Data Index: 188535 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.9762. Min Act: -0.0002

Data Index: 1276652 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.9403. Min Act: -0.0002

Data Index: 312952 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.9614. Min Act: -0.0002

Data Index: 209445 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.9529. Min Act: -0.0002

Data Index: 996108 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.9352. Min Act: -0.0002

Data Index: 141751 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.8824. Min Act: -0.0002

Data Index: 556254 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.8284. Min Act: -0.0002

Data Index: 812000 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.8775. Min Act: -0.0002

Data Index: 852055 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.8727. Min Act: -0.0002

Data Index: 365243 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.8693. Min Act: -0.0002

Data Index: 509940 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.8973. Min Act: -0.0002

Data Index: 202750 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.8936. Min Act: -0.0002

Data Index: 434873 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.2891. Min Range: -1.2891

Max Act: 0.8572. Min Act: -0.0002

Data Index: 37272 (C4 (Web Text))

Max Activating Token Index: 984