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

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

Neuron 963 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.2190. Min Act: -0.0001

Data Index: 346491 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1984. Min Act: -0.0000

Data Index: 824064 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.2110. Min Act: -0.0001

Data Index: 322948 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1181309 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.2087. Min Act: -0.0001

Data Index: 173690 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.2021. Min Act: -0.0001

Data Index: 169511 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1107183 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1884. Min Act: -0.0001

Data Index: 673175 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1824. Min Act: -0.0000

Data Index: 108389 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1954. Min Act: -0.0001

Data Index: 548047 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1858. Min Act: -0.0001

Data Index: 558941 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.2146. Min Act: -0.0001

Data Index: 565261 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1816. Min Act: -0.0001

Data Index: 999488 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1826. Min Act: -0.0001

Data Index: 834499 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1787. Min Act: -0.0001

Data Index: 835753 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1004789 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1833. Min Act: -0.0001

Data Index: 563879 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1813. Min Act: -0.0001

Data Index: 572970 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1801. Min Act: -0.0001

Data Index: 509272 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1863. Min Act: -0.0001

Data Index: 43717 (C4 (Web Text))

Max Activating Token Index: 796