Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1812 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1897. Min Act: -0.0002

Data Index: 57430 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1426. Min Act: -0.0001

Data Index: 671789 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0291. Min Act: -0.0002

Data Index: 1299617 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8126. Min Act: -0.0001

Data Index: 12035 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9635. Min Act: -0.0001

Data Index: 1022414 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.2159. Min Act: -0.0002

Data Index: 818214 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1714. Min Act: -0.0002

Data Index: 909611 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9731. Min Act: -0.0002

Data Index: 999444 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.7922. Min Act: -0.0001

Data Index: 836799 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9583. Min Act: -0.0001

Data Index: 124692 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.6916. Min Act: -0.0001

Data Index: 229644 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8477. Min Act: -0.0002

Data Index: 912585 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8420. Min Act: -0.0001

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9629. Min Act: -0.0002

Data Index: 1203978 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8143. Min Act: -0.0002

Data Index: 731424 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8145. Min Act: -0.0002

Data Index: 327252 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.4955. Min Act: -0.0001

Data Index: 618029 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9259. Min Act: -0.0002

Data Index: 704302 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0138. Min Act: -0.0001

Data Index: 216988 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.6648. Min Act: -0.0002

Data Index: 68098 (C4 (Web Text))

Max Activating Token Index: 621