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

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

Neuron 1067 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: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1571982 (Python Code)

Max Activating Token Index: 595

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0596. Min Act: -0.0002

Data Index: 453268 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1355936 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0417. Min Act: -0.0001

Data Index: 614808 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0410. Min Act: -0.0001

Data Index: 202516 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0410. Min Act: -0.0000

Data Index: 777172 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1481432 (Python Code)

Max Activating Token Index: 218

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1565219 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1440182 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0368. Min Act: 0.0000

Data Index: 204642 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0386. Min Act: 0.0000

Data Index: 927095 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0373. Min Act: 0.0000

Data Index: 604206 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1347368 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0382. Min Act: -0.0001

Data Index: 739049 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0345. Min Act: -0.0001

Data Index: 5467 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0372. Min Act: 0.0000

Data Index: 970652 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1106022 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0365. Min Act: 0.0000

Data Index: 574882 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0361. Min Act: -0.0001

Data Index: 579211 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0361. Min Act: 0.0001

Data Index: 1306411 (C4 (Web Text))

Max Activating Token Index: 1009