Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1989 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.5344. Min Act: -0.0005

Data Index: 954907 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4471. Min Act: -0.0005

Data Index: 1024838 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.5063. Min Act: -0.0005

Data Index: 268709 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4496. Min Act: -0.0005

Data Index: 1066459 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4796. Min Act: -0.0005

Data Index: 5755 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4890. Min Act: -0.0005

Data Index: 482230 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3890. Min Act: -0.0005

Data Index: 161591 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3908. Min Act: -0.0005

Data Index: 695054 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4301. Min Act: -0.0005

Data Index: 743949 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4092. Min Act: -0.0005

Data Index: 709469 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4444. Min Act: -0.0005

Data Index: 526073 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3681. Min Act: -0.0005

Data Index: 1202065 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4735. Min Act: -0.0005

Data Index: 737907 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3838. Min Act: -0.0005

Data Index: 916879 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4669. Min Act: -0.0005

Data Index: 103818 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4075. Min Act: -0.0005

Data Index: 935394 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4184. Min Act: -0.0005

Data Index: 1141928 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3614. Min Act: -0.0005

Data Index: 1339620 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4298. Min Act: -0.0005

Data Index: 938524 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3996. Min Act: -0.0005

Data Index: 1154670 (C4 (Web Text))

Max Activating Token Index: 61