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

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

Neuron 3038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0721. Min Range: -1.0721

Max Act: 1.0580. Min Act: -0.0000

Data Index: 1250421 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.0721. Min Range: -1.0721

Max Act: 1.0149. Min Act: -0.0000

Data Index: 242458 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.0721. Min Range: -1.0721

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1427369 (Python Code)

Max Activating Token Index: 890

Text #3

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1439748 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1332835 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.8318. Min Act: -0.0000

Data Index: 503215 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1018173 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1031781 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7187. Min Act: -0.0000

Data Index: 902441 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1440883 (Python Code)

Max Activating Token Index: 191

Text #10

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.6431. Min Act: -0.0000

Data Index: 584511 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1391475 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1357940 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1087119 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7201. Min Act: -0.0000

Data Index: 961665 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7407. Min Act: -0.0000

Data Index: 905727 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1303047 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.6189. Min Act: -0.0000

Data Index: 293089 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1430230 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 1.0721. Min Range: -1.0721

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1200923 (C4 (Web Text))

Max Activating Token Index: 387