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

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

Neuron 3013 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2536. Min Act: -0.0001

Data Index: 837710 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2380. Min Act: -0.0001

Data Index: 414234 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1034853 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1151957 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2028. Min Act: -0.0001

Data Index: 186579 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2046. Min Act: -0.0001

Data Index: 186210 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2029. Min Act: -0.0001

Data Index: 572319 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2415. Min Act: -0.0001

Data Index: 576829 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1247479 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1997. Min Act: -0.0001

Data Index: 162960 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1037973 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2202. Min Act: -0.0001

Data Index: 12962 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1174568 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1279307 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1169160 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1205332 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1306388 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1869. Min Act: -0.0001

Data Index: 210496 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1947. Min Act: -0.0001

Data Index: 659680 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1908. Min Act: -0.0001

Data Index: 365233 (C4 (Web Text))

Max Activating Token Index: 285