Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1882 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.9433. Min Act: -0.0000

Data Index: 140405 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.5649. Min Act: -0.0000

Data Index: 422235 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.6810. Min Act: -0.0000

Data Index: 664373 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.3585. Min Act: -0.0000

Data Index: 1268405 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.4519. Min Act: -0.0000

Data Index: 374972 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.2377. Min Act: -0.0000

Data Index: 1160855 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.2437. Min Act: -0.0000

Data Index: 893102 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.1970. Min Act: -0.0000

Data Index: 986557 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.4174. Min Act: -0.0000

Data Index: 588928 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.0655. Min Act: -0.0000

Data Index: 952667 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1117782 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.1120. Min Act: -0.0000

Data Index: 1207547 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 2.9433. Min Range: -2.9433

Max Act: 1.9914. Min Act: -0.0000

Data Index: 1075410 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 2.9433. Min Range: -2.9433

Max Act: 1.9548. Min Act: -0.0000

Data Index: 693798 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 2.9433. Min Range: -2.9433

Max Act: 1.9428. Min Act: -0.0000

Data Index: 305778 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.0531. Min Act: -0.0000

Data Index: 1280152 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.2559. Min Act: -0.0000

Data Index: 273395 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 2.9433. Min Range: -2.9433

Max Act: 1.9314. Min Act: -0.0000

Data Index: 1068533 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.9433. Min Range: -2.9433

Max Act: 2.0349. Min Act: -0.0000

Data Index: 651612 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 2.9433. Min Range: -2.9433

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1328611 (C4 (Web Text))

Max Activating Token Index: 830