Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1119 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1284275 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0849. Min Act: -0.0001

Data Index: 905514 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1075207 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0767. Min Act: -0.0001

Data Index: 587461 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0751. Min Act: -0.0001

Data Index: 554535 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0708. Min Act: -0.0001

Data Index: 753986 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1206054 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0761. Min Act: -0.0001

Data Index: 354504 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0720. Min Act: -0.0001

Data Index: 854168 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0722. Min Act: -0.0001

Data Index: 555886 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1279702 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1265342 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0688. Min Act: -0.0001

Data Index: 661193 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0677. Min Act: -0.0001

Data Index: 116937 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1180988 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1197596 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0719. Min Act: -0.0001

Data Index: 971320 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1290855 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0759. Min Act: -0.0001

Data Index: 413929 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1325350 (C4 (Web Text))

Max Activating Token Index: 668