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

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

Neuron 4974 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1012. Min Range: -1.1012

Max Act: 1.1012. Min Act: -0.0000

Data Index: 276512 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.8270. Min Act: -0.0000

Data Index: 53442 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.8548. Min Act: -0.0000

Data Index: 479966 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.8390. Min Act: -0.0000

Data Index: 474621 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.7720. Min Act: -0.0000

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.8013. Min Act: -0.0000

Data Index: 59272 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1176701 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1339682 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1048561 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1240419 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1269298 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.5858. Min Act: -0.0000

Data Index: 9479 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.5975. Min Act: -0.0000

Data Index: 16302 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.6126. Min Act: -0.0000

Data Index: 741390 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.5958. Min Act: -0.0000

Data Index: 989845 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.6123. Min Act: -0.0000

Data Index: 294677 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.5761. Min Act: -0.0000

Data Index: 395228 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.5723. Min Act: -0.0000

Data Index: 417518 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.5448. Min Act: -0.0000

Data Index: 385297 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.1012. Min Range: -1.1012

Max Act: 0.5527. Min Act: -0.0000

Data Index: 76269 (C4 (Web Text))

Max Activating Token Index: 509