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

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

Neuron 889 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7864. Min Range: -2.7864

Max Act: 2.7864. Min Act: -0.0000

Data Index: 802467 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 2.7864. Min Range: -2.7864

Max Act: 2.6088. Min Act: -0.0000

Data Index: 528684 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 2.7864. Min Range: -2.7864

Max Act: 2.2072. Min Act: -0.0000

Data Index: 235970 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 2.7864. Min Range: -2.7864

Max Act: 2.0362. Min Act: -0.0000

Data Index: 355238 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.7864. Min Range: -2.7864

Max Act: 2.0509. Min Act: -0.0000

Data Index: 1041853 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.8198. Min Act: -0.0000

Data Index: 253321 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.9565. Min Act: -0.0000

Data Index: 658362 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.8143. Min Act: -0.0000

Data Index: 797730 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.7209. Min Act: -0.0000

Data Index: 822581 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1290719 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.7305. Min Act: -0.0000

Data Index: 1333115 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.8136. Min Act: -0.0000

Data Index: 1273701 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1428672 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.9094. Min Act: -0.0000

Data Index: 290677 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.7375. Min Act: -0.0000

Data Index: 1274280 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.7081. Min Act: -0.0000

Data Index: 1135301 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1124895 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.7209. Min Act: -0.0000

Data Index: 634175 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.7032. Min Act: -0.0000

Data Index: 86915 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 2.7864. Min Range: -2.7864

Max Act: 1.7137. Min Act: -0.0000

Data Index: 991429 (C4 (Web Text))

Max Activating Token Index: 173