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

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

Neuron 1891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.8666. Min Act: -0.0001

Data Index: 1584914 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.9201. Min Act: -0.0000

Data Index: 520039 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.8389. Min Act: -0.0000

Data Index: 372715 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.8871. Min Act: -0.0000

Data Index: 620214 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.8176. Min Act: -0.0000

Data Index: 599276 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.6438. Min Act: -0.0000

Data Index: 177811 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.8336. Min Act: -0.0001

Data Index: 816065 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.7348. Min Act: -0.0000

Data Index: 1245128 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1549181 (Python Code)

Max Activating Token Index: 772

Text #9

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.7192. Min Act: -0.0000

Data Index: 984125 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.8797. Min Act: -0.0000

Data Index: 375267 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.6516. Min Act: -0.0000

Data Index: 790963 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.6435. Min Act: -0.0000

Data Index: 710769 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.6514. Min Act: -0.0000

Data Index: 651010 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.7151. Min Act: -0.0000

Data Index: 537016 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.6115. Min Act: -0.0000

Data Index: 441561 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.6221. Min Act: -0.0000

Data Index: 192805 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.5026. Min Act: -0.0001

Data Index: 207118 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.4830. Min Act: -0.0000

Data Index: 428019 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 1.9201. Min Range: -1.9201

Max Act: 1.4540. Min Act: -0.0001

Data Index: 1531411 (Python Code)

Max Activating Token Index: 258