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

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

Neuron 5308 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: 0.6079. Min Range: -0.6079

Max Act: 0.5749. Min Act: -0.0000

Data Index: 166171 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1313813 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1228996 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1533888 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5148. Min Act: -0.0000

Data Index: 527174 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1215958 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5005. Min Act: -0.0000

Data Index: 3918 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5368. Min Act: -0.0000

Data Index: 843956 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5029. Min Act: -0.0000

Data Index: 220098 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4852. Min Act: -0.0000

Data Index: 85239 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5076. Min Act: -0.0000

Data Index: 83683 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4612. Min Act: -0.0001

Data Index: 440034 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1129992 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4699. Min Act: -0.0000

Data Index: 592440 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4491. Min Act: -0.0000

Data Index: 341439 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4805. Min Act: -0.0000

Data Index: 540872 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4731. Min Act: -0.0000

Data Index: 339422 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4715. Min Act: -0.0000

Data Index: 759593 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1195769 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4351. Min Act: -0.0001

Data Index: 943248 (C4 (Web Text))

Max Activating Token Index: 487