Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1005685 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.1793. Min Act: -0.0000

Data Index: 127125 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1058981 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.1413. Min Act: -0.0000

Data Index: 1237135 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.1947. Min Act: -0.0000

Data Index: 1129581 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.0810. Min Act: -0.0000

Data Index: 482093 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9747. Min Act: -0.0000

Data Index: 889889 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.0449. Min Act: -0.0000

Data Index: 176514 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1037682 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.0307. Min Act: -0.0000

Data Index: 665832 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.4723. Min Range: -1.4723

Max Act: 1.0045. Min Act: -0.0000

Data Index: 300383 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9133. Min Act: -0.0000

Data Index: 36363 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9965. Min Act: -0.0000

Data Index: 450643 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9786. Min Act: -0.0000

Data Index: 873996 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1265994 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.8567. Min Act: -0.0000

Data Index: 591126 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.8659. Min Act: -0.0000

Data Index: 839903 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1210745 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9426. Min Act: -0.0000

Data Index: 666543 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.4723. Min Range: -1.4723

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1077695 (C4 (Web Text))

Max Activating Token Index: 314