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

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

Neuron 407 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0002

Data Index: 952676 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0478. Min Act: -0.0002

Data Index: 650823 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0476. Min Act: -0.0002

Data Index: 839028 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0463. Min Act: -0.0002

Data Index: 365499 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0455. Min Act: -0.0002

Data Index: 274364 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0438. Min Act: -0.0002

Data Index: 885699 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0424. Min Act: -0.0002

Data Index: 172768 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1002770 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0412. Min Act: -0.0002

Data Index: 227035 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0433. Min Act: -0.0002

Data Index: 785245 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0417. Min Act: -0.0002

Data Index: 151231 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0422. Min Act: -0.0002

Data Index: 381053 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0395. Min Act: -0.0002

Data Index: 829359 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1018858 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0400. Min Act: -0.0002

Data Index: 998420 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0391. Min Act: -0.0002

Data Index: 970492 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1294567 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0393. Min Act: -0.0002

Data Index: 833826 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0381. Min Act: -0.0002

Data Index: 998981 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0385. Min Act: -0.0002

Data Index: 736988 (C4 (Web Text))

Max Activating Token Index: 584