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

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

Neuron 1745 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.4894. Min Act: -0.0000

Data Index: 22531 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0478. Min Act: -0.0001

Data Index: 101250 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9853. Min Act: -0.0001

Data Index: 771314 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9554. Min Act: -0.0001

Data Index: 336357 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9518. Min Act: -0.0001

Data Index: 1059799 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.4894. Min Range: -1.4894

Max Act: 1.0429. Min Act: -0.0001

Data Index: 1273899 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.9017. Min Act: -0.0001

Data Index: 817899 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.8474. Min Act: -0.0001

Data Index: 274651 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.8698. Min Act: -0.0001

Data Index: 724328 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.8465. Min Act: -0.0000

Data Index: 28611 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.8306. Min Act: -0.0001

Data Index: 793786 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.8448. Min Act: -0.0001

Data Index: 174823 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.8421. Min Act: -0.0001

Data Index: 495514 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.8163. Min Act: -0.0001

Data Index: 109455 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1249146 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.7215. Min Act: -0.0000

Data Index: 361354 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.7175. Min Act: -0.0001

Data Index: 276399 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.7503. Min Act: -0.0001

Data Index: 542334 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1131061 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.4894. Min Range: -1.4894

Max Act: 0.6446. Min Act: -0.0000

Data Index: 943700 (C4 (Web Text))

Max Activating Token Index: 527