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

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

Neuron 1212 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3918. Min Range: -1.3918

Max Act: 1.3918. Min Act: -0.0000

Data Index: 495395 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 1.3918. Min Range: -1.3918

Max Act: 1.3124. Min Act: -0.0000

Data Index: 440890 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 1.3918. Min Range: -1.3918

Max Act: 1.1935. Min Act: -0.0000

Data Index: 1297771 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 1.3918. Min Range: -1.3918

Max Act: 1.1891. Min Act: -0.0000

Data Index: 1268346 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.3918. Min Range: -1.3918

Max Act: 1.1128. Min Act: -0.0000

Data Index: 695635 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.3918. Min Range: -1.3918

Max Act: 1.0547. Min Act: -0.0000

Data Index: 773206 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.3918. Min Range: -1.3918

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1257542 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.3918. Min Range: -1.3918

Max Act: 1.0054. Min Act: -0.0000

Data Index: 98024 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1044785 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9557. Min Act: -0.0000

Data Index: 957519 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1273336 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9856. Min Act: -0.0000

Data Index: 232156 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1235587 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9378. Min Act: -0.0000

Data Index: 731974 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9816. Min Act: -0.0000

Data Index: 683493 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9481. Min Act: -0.0000

Data Index: 729993 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.8928. Min Act: -0.0000

Data Index: 448592 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9175. Min Act: -0.0000

Data Index: 296384 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1263220 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.3918. Min Range: -1.3918

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1223401 (C4 (Web Text))

Max Activating Token Index: 650