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

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

Neuron 2645 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: 0.8546. Min Range: -0.8546

Max Act: 0.8546. Min Act: -0.0001

Data Index: 1048217 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6988. Min Act: -0.0001

Data Index: 278474 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6680. Min Act: -0.0001

Data Index: 90130 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6850. Min Act: -0.0001

Data Index: 1047978 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6895. Min Act: -0.0001

Data Index: 894717 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6890. Min Act: -0.0001

Data Index: 981725 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6214. Min Act: -0.0001

Data Index: 412111 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6019. Min Act: -0.0001

Data Index: 580994 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6140. Min Act: -0.0001

Data Index: 672366 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6468. Min Act: -0.0001

Data Index: 702897 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6058. Min Act: -0.0001

Data Index: 525552 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6601. Min Act: -0.0001

Data Index: 239528 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6006. Min Act: -0.0001

Data Index: 372324 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5886. Min Act: -0.0001

Data Index: 544048 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6197. Min Act: -0.0001

Data Index: 8005 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6067. Min Act: -0.0001

Data Index: 1162348 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6402. Min Act: -0.0001

Data Index: 109987 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6030. Min Act: -0.0001

Data Index: 431902 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5827. Min Act: -0.0001

Data Index: 578114 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6038. Min Act: -0.0001

Data Index: 1120759 (C4 (Web Text))

Max Activating Token Index: 18