Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 688 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: 0.0001

Data Index: 261246 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0641. Min Act: 0.0001

Data Index: 622268 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0608. Min Act: -0.0002

Data Index: 213241 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1631534 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0592. Min Act: -0.0002

Data Index: 881302 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0559. Min Act: -0.0002

Data Index: 619101 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1652327 (Python Code)

Max Activating Token Index: 1001

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0455. Min Act: 0.0001

Data Index: 913453 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0419. Min Act: -0.0002

Data Index: 562106 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0425. Min Act: -0.0002

Data Index: 171374 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1656908 (Python Code)

Max Activating Token Index: 857

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0439. Min Act: -0.0001

Data Index: 125767 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0395. Min Act: 0.0001

Data Index: 254344 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0425. Min Act: 0.0000

Data Index: 1084187 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0413. Min Act: -0.0001

Data Index: 756618 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0441. Min Act: -0.0000

Data Index: 516651 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0381. Min Act: 0.0001

Data Index: 188408 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0388. Min Act: 0.0001

Data Index: 262808 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0404. Min Act: 0.0001

Data Index: 971479 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0385. Min Act: 0.0001

Data Index: 1249416 (C4 (Web Text))

Max Activating Token Index: 935