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

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

Neuron 1935 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1556773 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0000

Data Index: 373457 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0550. Min Act: -0.0001

Data Index: 542341 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0469. Min Act: -0.0001

Data Index: 568845 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1353760 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1061502 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1516346 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1180922 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1542840 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0412. Min Act: -0.0001

Data Index: 838384 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0406. Min Act: -0.0001

Data Index: 958585 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0435. Min Act: -0.0000

Data Index: 867742 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1233114 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0407. Min Act: -0.0000

Data Index: 203830 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0424. Min Act: -0.0000

Data Index: 331018 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0375. Min Act: -0.0001

Data Index: 153906 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0401. Min Act: -0.0001

Data Index: 103637 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0415. Min Act: -0.0001

Data Index: 712319 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1202470 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1388535 (Python Code)

Max Activating Token Index: 606