Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 635 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0487. Min Act: -0.0001

Data Index: 105532 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1521191 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0471. Min Act: -0.0001

Data Index: 632219 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0443. Min Act: -0.0001

Data Index: 949378 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0438. Min Act: -0.0001

Data Index: 537754 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0433. Min Act: -0.0001

Data Index: 54162 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0379. Min Act: -0.0001

Data Index: 791389 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0389. Min Act: -0.0001

Data Index: 1306586 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1401219 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0375. Min Act: -0.0001

Data Index: 447912 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1605640 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0370. Min Act: -0.0001

Data Index: 622383 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0339. Min Act: -0.0001

Data Index: 808946 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1398437 (Python Code)

Max Activating Token Index: 358

Text #14

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1518353 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0344. Min Act: -0.0001

Data Index: 772834 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1399240 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1654341 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0309. Min Act: -0.0001

Data Index: 343508 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0354. Min Act: -0.0001

Data Index: 314319 (C4 (Web Text))

Max Activating Token Index: 591