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

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

Neuron 743 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: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0002

Data Index: 707002 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0516. Min Act: -0.0002

Data Index: 636812 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0508. Min Act: -0.0002

Data Index: 269360 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0484. Min Act: -0.0002

Data Index: 664137 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0477. Min Act: -0.0002

Data Index: 258137 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0481. Min Act: -0.0002

Data Index: 360419 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0476. Min Act: -0.0002

Data Index: 473543 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0471. Min Act: -0.0002

Data Index: 269445 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0489. Min Act: -0.0002

Data Index: 908110 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0483. Min Act: -0.0002

Data Index: 7631 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0467. Min Act: -0.0002

Data Index: 545948 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0461. Min Act: -0.0002

Data Index: 319848 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0451. Min Act: -0.0001

Data Index: 9077 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0476. Min Act: -0.0002

Data Index: 45571 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1268704 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1141800 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0469. Min Act: -0.0002

Data Index: 819205 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0465. Min Act: -0.0002

Data Index: 916913 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0462. Min Act: -0.0002

Data Index: 789941 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1032352 (C4 (Web Text))

Max Activating Token Index: 91