Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3273 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.5373. Min Range: -7.5373

Max Act: 7.5373. Min Act: -0.0000

Data Index: 664259 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 7.5373. Min Range: -7.5373

Max Act: 6.0540. Min Act: -0.0001

Data Index: 457414 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 7.5373. Min Range: -7.5373

Max Act: 6.3777. Min Act: -0.0001

Data Index: 1024055 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.8295. Min Act: -0.0001

Data Index: 518642 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 7.5373. Min Range: -7.5373

Max Act: 6.0993. Min Act: -0.0001

Data Index: 425622 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.8534. Min Act: -0.0000

Data Index: 275337 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.6774. Min Act: -0.0001

Data Index: 464670 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.5802. Min Act: -0.0001

Data Index: 1209170 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.4377. Min Act: -0.0000

Data Index: 501757 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.5292. Min Act: -0.0000

Data Index: 840510 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.1419. Min Act: -0.0000

Data Index: 810444 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.6666. Min Act: -0.0001

Data Index: 517101 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.4168. Min Act: -0.0000

Data Index: 790448 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 7.5373. Min Range: -7.5373

Max Act: 4.9736. Min Act: -0.0000

Data Index: 332672 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.1155. Min Act: -0.0000

Data Index: 677827 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.0508. Min Act: -0.0001

Data Index: 400431 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 7.5373. Min Range: -7.5373

Max Act: 5.0200. Min Act: -0.0001

Data Index: 460630 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 7.5373. Min Range: -7.5373

Max Act: 4.6478. Min Act: -0.0000

Data Index: 208911 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 7.5373. Min Range: -7.5373

Max Act: 4.7858. Min Act: -0.0000

Data Index: 238045 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 7.5373. Min Range: -7.5373

Max Act: 4.6933. Min Act: -0.0001

Data Index: 881207 (C4 (Web Text))

Max Activating Token Index: 803