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

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

Neuron 1112 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0600. Min Range: -1.0600

Max Act: 1.0600. Min Act: -0.0001

Data Index: 809107 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.0600. Min Range: -1.0600

Max Act: 1.0162. Min Act: -0.0001

Data Index: 371300 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.9303. Min Act: -0.0001

Data Index: 596833 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8665. Min Act: -0.0001

Data Index: 1894 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.9197. Min Act: -0.0001

Data Index: 499427 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.9141. Min Act: -0.0001

Data Index: 673501 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8981. Min Act: -0.0001

Data Index: 1292998 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.9233. Min Act: -0.0001

Data Index: 12165 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.9146. Min Act: -0.0001

Data Index: 756433 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.9081. Min Act: -0.0001

Data Index: 1058262 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8322. Min Act: -0.0001

Data Index: 138319 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7688. Min Act: -0.0001

Data Index: 1255093 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8967. Min Act: -0.0001

Data Index: 813183 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8077. Min Act: -0.0001

Data Index: 1050787 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8699. Min Act: -0.0001

Data Index: 904847 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8292. Min Act: -0.0001

Data Index: 1261447 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8292. Min Act: -0.0001

Data Index: 1049150 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8854. Min Act: -0.0001

Data Index: 569927 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.7937. Min Act: -0.0001

Data Index: 218360 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 1.0600. Min Range: -1.0600

Max Act: 0.8136. Min Act: -0.0001

Data Index: 1195226 (C4 (Web Text))

Max Activating Token Index: 125