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

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

Neuron 5064 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0002

Data Index: 310808 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0463. Min Act: -0.0002

Data Index: 73579 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0002

Data Index: 982357 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0002

Data Index: 356600 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0002

Data Index: 151803 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0465. Min Act: -0.0002

Data Index: 167618 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0456. Min Act: -0.0001

Data Index: 81419 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0449. Min Act: -0.0002

Data Index: 696733 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0436. Min Act: -0.0001

Data Index: 750569 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0432. Min Act: -0.0002

Data Index: 566959 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0439. Min Act: -0.0002

Data Index: 592706 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0431. Min Act: -0.0001

Data Index: 836 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1053902 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1229862 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0422. Min Act: -0.0002

Data Index: 458662 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0426. Min Act: -0.0002

Data Index: 586706 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1000551 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0416. Min Act: -0.0002

Data Index: 136147 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0416. Min Act: -0.0002

Data Index: 442108 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1329644 (C4 (Web Text))

Max Activating Token Index: 740