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

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

Neuron 2715 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.6326. Min Act: -0.0001

Data Index: 1035179 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5880. Min Act: -0.0000

Data Index: 390925 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5857. Min Act: -0.0000

Data Index: 469191 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1192596 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5495. Min Act: -0.0000

Data Index: 196171 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1227516 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4679. Min Act: -0.0000

Data Index: 685104 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5312. Min Act: -0.0000

Data Index: 839865 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5878. Min Act: -0.0000

Data Index: 171421 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5326. Min Act: 0.0000

Data Index: 1309304 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5152. Min Act: -0.0000

Data Index: 214865 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5015. Min Act: -0.0000

Data Index: 981894 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4926. Min Act: -0.0000

Data Index: 29488 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5100. Min Act: -0.0000

Data Index: 827384 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4553. Min Act: -0.0000

Data Index: 314933 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4664. Min Act: -0.0000

Data Index: 24750 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4421. Min Act: -0.0000

Data Index: 849734 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4709. Min Act: -0.0000

Data Index: 352092 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4274. Min Act: -0.0000

Data Index: 753042 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4414. Min Act: -0.0000

Data Index: 954735 (C4 (Web Text))

Max Activating Token Index: 462