Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2648 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.9340. Min Act: -0.0000

Data Index: 353925 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7624. Min Act: -0.0000

Data Index: 650462 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7285. Min Act: -0.0000

Data Index: 811809 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6752. Min Act: -0.0000

Data Index: 289663 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6926. Min Act: -0.0000

Data Index: 87635 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6439. Min Act: -0.0000

Data Index: 353502 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6505. Min Act: -0.0000

Data Index: 27348 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6591. Min Act: -0.0000

Data Index: 357726 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1267202 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1089801 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1199546 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5698. Min Act: -0.0000

Data Index: 940786 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1020671 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.4979. Min Act: -0.0000

Data Index: 646106 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5420. Min Act: -0.0000

Data Index: 605256 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5253. Min Act: -0.0000

Data Index: 334465 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5062. Min Act: -0.0000

Data Index: 841498 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5060. Min Act: -0.0000

Data Index: 272924 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.4922. Min Act: -0.0000

Data Index: 699423 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1064147 (C4 (Web Text))

Max Activating Token Index: 156