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

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

Neuron 4432 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0002

Data Index: 391810 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0584. Min Act: -0.0002

Data Index: 380727 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0584. Min Act: -0.0002

Data Index: 468433 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1090528 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0488. Min Act: -0.0002

Data Index: 350801 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0496. Min Act: -0.0002

Data Index: 532268 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0479. Min Act: -0.0002

Data Index: 646010 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0455. Min Act: -0.0002

Data Index: 512343 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0445. Min Act: -0.0002

Data Index: 514874 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0427. Min Act: -0.0002

Data Index: 565024 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0419. Min Act: -0.0002

Data Index: 501121 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1187567 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0409. Min Act: -0.0002

Data Index: 101884 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0406. Min Act: -0.0002

Data Index: 220586 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1085720 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1205247 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0392. Min Act: -0.0002

Data Index: 482421 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0402. Min Act: -0.0002

Data Index: 74168 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0384. Min Act: -0.0002

Data Index: 188259 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1232815 (C4 (Web Text))

Max Activating Token Index: 41