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

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

Neuron 845 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: 0.7242. Min Range: -0.7242

Max Act: 0.7242. Min Act: -0.0001

Data Index: 867439 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.6206. Min Act: -0.0001

Data Index: 886442 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.6338. Min Act: -0.0001

Data Index: 813168 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.6314. Min Act: -0.0001

Data Index: 1120598 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5781. Min Act: -0.0001

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.6222. Min Act: -0.0001

Data Index: 662504 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5705. Min Act: -0.0001

Data Index: 1262476 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.6644. Min Act: -0.0001

Data Index: 527743 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4850. Min Act: -0.0001

Data Index: 601670 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5135. Min Act: -0.0001

Data Index: 555201 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5453. Min Act: -0.0001

Data Index: 1059924 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5525. Min Act: -0.0001

Data Index: 1124818 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5167. Min Act: -0.0001

Data Index: 295000 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5279. Min Act: -0.0001

Data Index: 546082 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4882. Min Act: -0.0001

Data Index: 1111910 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.5375. Min Act: -0.0001

Data Index: 893777 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4814. Min Act: -0.0001

Data Index: 48971 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4653. Min Act: -0.0001

Data Index: 1520707 (Python Code)

Max Activating Token Index: 598

Text #18

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4882. Min Act: -0.0001

Data Index: 698483 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.7242. Min Range: -0.7242

Max Act: 0.4453. Min Act: -0.0001

Data Index: 61687 (C4 (Web Text))

Max Activating Token Index: 679