Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3767 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0001

Data Index: 636663 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1207. Min Act: -0.0000

Data Index: 157622 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1077. Min Act: -0.0001

Data Index: 99565 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1102. Min Act: -0.0001

Data Index: 540536 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1017. Min Act: -0.0000

Data Index: 161846 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1060. Min Act: -0.0001

Data Index: 714032 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1010. Min Act: -0.0001

Data Index: 744153 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1050. Min Act: -0.0001

Data Index: 689278 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1036553 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0965. Min Act: -0.0000

Data Index: 599609 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0952. Min Act: -0.0001

Data Index: 257561 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0983. Min Act: -0.0000

Data Index: 583296 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0935. Min Act: -0.0000

Data Index: 216090 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1088425 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0984. Min Act: -0.0000

Data Index: 39481 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0972. Min Act: -0.0001

Data Index: 155471 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1317098 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0936. Min Act: -0.0000

Data Index: 434266 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0916. Min Act: -0.0000

Data Index: 362545 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0951. Min Act: -0.0000

Data Index: 85126 (C4 (Web Text))

Max Activating Token Index: 86