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

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

Neuron 68 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8337. Min Range: -2.8337

Max Act: 2.8337. Min Act: -0.0000

Data Index: 477065 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 2.8337. Min Range: -2.8337

Max Act: 2.2537. Min Act: -0.0000

Data Index: 577154 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 2.8337. Min Range: -2.8337

Max Act: 2.1151. Min Act: -0.0000

Data Index: 712603 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 2.8337. Min Range: -2.8337

Max Act: 2.1971. Min Act: -0.0000

Data Index: 830905 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.8724. Min Act: -0.0000

Data Index: 673733 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.8676. Min Act: -0.0000

Data Index: 1070261 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 2.8337. Min Range: -2.8337

Max Act: 2.0816. Min Act: -0.0000

Data Index: 1044192 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.5867. Min Act: -0.0000

Data Index: 781893 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.8797. Min Act: -0.0000

Data Index: 1258963 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.9944. Min Act: -0.0000

Data Index: 1147957 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.7842. Min Act: -0.0000

Data Index: 15535 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.9426. Min Act: -0.0000

Data Index: 301496 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.8013. Min Act: -0.0000

Data Index: 1086199 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.9273. Min Act: -0.0000

Data Index: 1248373 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.6391. Min Act: -0.0000

Data Index: 872125 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.8241. Min Act: -0.0000

Data Index: 233781 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.8783. Min Act: -0.0000

Data Index: 297111 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.6581. Min Act: -0.0000

Data Index: 559789 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1334787 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 2.8337. Min Range: -2.8337

Max Act: 1.6827. Min Act: -0.0000

Data Index: 738952 (C4 (Web Text))

Max Activating Token Index: 144