Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 897 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0006

Data Index: 283708 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0432. Min Act: -0.0006

Data Index: 861972 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1228065 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0425. Min Act: -0.0006

Data Index: 686695 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0412. Min Act: -0.0006

Data Index: 1108443 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0400. Min Act: -0.0006

Data Index: 749126 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0374. Min Act: -0.0006

Data Index: 212478 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0388. Min Act: -0.0006

Data Index: 184211 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0380. Min Act: -0.0005

Data Index: 815784 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0392. Min Act: -0.0006

Data Index: 848651 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0372. Min Act: -0.0006

Data Index: 447688 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0375. Min Act: -0.0006

Data Index: 916634 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0359. Min Act: -0.0005

Data Index: 1188011 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0366. Min Act: -0.0006

Data Index: 36821 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0371. Min Act: -0.0006

Data Index: 537097 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0380. Min Act: -0.0006

Data Index: 745601 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0366. Min Act: -0.0006

Data Index: 477194 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0372. Min Act: -0.0006

Data Index: 1289667 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0361. Min Act: -0.0006

Data Index: 943870 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0345. Min Act: -0.0006

Data Index: 68245 (C4 (Web Text))

Max Activating Token Index: 965