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

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

Neuron 1728 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.8349. Min Act: -0.0001

Data Index: 1234938 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7586. Min Act: -0.0001

Data Index: 966396 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.8184. Min Act: -0.0001

Data Index: 1331389 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7246. Min Act: -0.0001

Data Index: 1157621 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7835. Min Act: -0.0001

Data Index: 445852 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.7934. Min Act: -0.0001

Data Index: 908077 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6594. Min Act: -0.0001

Data Index: 64492 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6639. Min Act: -0.0001

Data Index: 777747 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.6279. Min Act: -0.0001

Data Index: 616563 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.5722. Min Act: -0.0001

Data Index: 854750 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.5199. Min Act: -0.0001

Data Index: 732446 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.5871. Min Act: -0.0001

Data Index: 344627 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.4017. Min Act: -0.0001

Data Index: 213570 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.4309. Min Act: -0.0001

Data Index: 135075 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.4347. Min Act: -0.0001

Data Index: 1196107 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.4197. Min Act: -0.0001

Data Index: 193978 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.4257. Min Act: -0.0001

Data Index: 461619 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.4393. Min Act: -0.0001

Data Index: 1519008 (Python Code)

Max Activating Token Index: 174

Text #18

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.4442. Min Act: -0.0001

Data Index: 440906 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.8349. Min Range: -0.8349

Max Act: 0.3999. Min Act: -0.0001

Data Index: 207593 (C4 (Web Text))

Max Activating Token Index: 7