Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 636 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0003

Data Index: 767900 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0364. Min Act: -0.0003

Data Index: 770631 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0360. Min Act: -0.0003

Data Index: 741153 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0343. Min Act: -0.0003

Data Index: 756813 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1053350 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0319. Min Act: -0.0003

Data Index: 128585 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0332. Min Act: -0.0003

Data Index: 969076 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0336. Min Act: -0.0003

Data Index: 421271 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1167681 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0332. Min Act: -0.0003

Data Index: 780861 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0333. Min Act: -0.0003

Data Index: 500192 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1302841 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1215102 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0331. Min Act: -0.0003

Data Index: 882009 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0331. Min Act: -0.0003

Data Index: 111826 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0324. Min Act: -0.0003

Data Index: 999566 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1071617 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0330. Min Act: -0.0003

Data Index: 133632 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0321. Min Act: -0.0003

Data Index: 974782 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1050618 (C4 (Web Text))

Max Activating Token Index: 452