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

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

Neuron 1584 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: 1.8852. Min Range: -1.8852

Max Act: 1.8852. Min Act: -0.0001

Data Index: 1327783 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.8167. Min Act: -0.0001

Data Index: 642775 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.7030. Min Act: -0.0001

Data Index: 1290127 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.7225. Min Act: -0.0000

Data Index: 619211 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.5416. Min Act: -0.0001

Data Index: 1437232 (Python Code)

Max Activating Token Index: 569

Text #5

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.3844. Min Act: -0.0001

Data Index: 52676 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.4773. Min Act: -0.0001

Data Index: 985224 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.4394. Min Act: -0.0001

Data Index: 1157773 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.5317. Min Act: -0.0001

Data Index: 647562 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.4833. Min Act: -0.0001

Data Index: 672579 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.3934. Min Act: -0.0000

Data Index: 927497 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.3831. Min Act: -0.0001

Data Index: 1123254 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.4574. Min Act: -0.0001

Data Index: 268817 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.4768. Min Act: -0.0001

Data Index: 1002052 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.3539. Min Act: -0.0001

Data Index: 393849 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.5508. Min Act: -0.0001

Data Index: 739048 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.2349. Min Act: -0.0001

Data Index: 793703 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.3129. Min Act: -0.0001

Data Index: 388339 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.2641. Min Act: -0.0001

Data Index: 413960 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 1.8852. Min Range: -1.8852

Max Act: 1.3030. Min Act: -0.0001

Data Index: 594011 (C4 (Web Text))

Max Activating Token Index: 897