Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 225 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.7580. Min Range: -1.7580

Max Act: 0.8740. Min Act: -0.0003

Data Index: 470589 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2633. Min Act: -0.0003

Data Index: 596685 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4415. Min Act: -0.0003

Data Index: 325414 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.5536. Min Act: -0.0003

Data Index: 377539 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2570. Min Act: -0.0003

Data Index: 658925 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.7580. Min Act: -0.0003

Data Index: 1183482 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.4237. Min Act: -0.0003

Data Index: 1118599 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2144. Min Act: -0.0003

Data Index: 1459 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2309. Min Act: -0.0003

Data Index: 1182781 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.5494. Min Act: -0.0003

Data Index: 253560 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.0420. Min Act: -0.0003

Data Index: 344272 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.0168. Min Act: -0.0003

Data Index: 544188 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.1411. Min Act: -0.0003

Data Index: 400621 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.5681. Min Act: -0.0003

Data Index: 92033 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.7580. Min Range: -1.7580

Max Act: 0.8760. Min Act: -0.0003

Data Index: 1022994 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.2319. Min Act: -0.0003

Data Index: 300914 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.7580. Min Range: -1.7580

Max Act: 1.0398. Min Act: -0.0003

Data Index: 686499 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 1.7580. Min Range: -1.7580

Max Act: 0.9593. Min Act: -0.0003

Data Index: 692780 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 1.7580. Min Range: -1.7580

Max Act: 0.9764. Min Act: -0.0003

Data Index: 731831 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.7580. Min Range: -1.7580

Max Act: 0.9313. Min Act: -0.0003

Data Index: 499516 (C4 (Web Text))

Max Activating Token Index: 375