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

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

Neuron 2459 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: 0.7451. Min Range: -0.7451

Max Act: 0.6662. Min Act: -0.0001

Data Index: 263578 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6851. Min Act: -0.0001

Data Index: 635337 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.7451. Min Act: -0.0001

Data Index: 1166128 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.7009. Min Act: -0.0001

Data Index: 627164 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6285. Min Act: -0.0001

Data Index: 848301 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6232. Min Act: -0.0001

Data Index: 624493 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6569. Min Act: -0.0001

Data Index: 579415 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.7026. Min Act: -0.0001

Data Index: 34429 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6697. Min Act: -0.0001

Data Index: 308276 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5952. Min Act: -0.0001

Data Index: 1232796 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6745. Min Act: -0.0001

Data Index: 504641 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6081. Min Act: -0.0001

Data Index: 1095031 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5651. Min Act: -0.0001

Data Index: 870449 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6193. Min Act: -0.0001

Data Index: 387829 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6298. Min Act: -0.0001

Data Index: 341034 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6267. Min Act: -0.0001

Data Index: 360133 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1113707 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6150. Min Act: -0.0001

Data Index: 825806 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6317. Min Act: -0.0001

Data Index: 226629 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5369. Min Act: -0.0001

Data Index: 18922 (C4 (Web Text))

Max Activating Token Index: 773