Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1322 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1049775 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0003

Data Index: 81955 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1039965 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1132248 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0473. Min Act: -0.0002

Data Index: 744897 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0513. Min Act: -0.0002

Data Index: 532971 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0523. Min Act: -0.0002

Data Index: 348709 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0514. Min Act: -0.0002

Data Index: 123312 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0463. Min Act: -0.0002

Data Index: 175357 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1343660 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0463. Min Act: -0.0002

Data Index: 245265 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0482. Min Act: -0.0002

Data Index: 27278 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0490. Min Act: -0.0002

Data Index: 665446 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0485. Min Act: -0.0002

Data Index: 443491 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0476. Min Act: -0.0002

Data Index: 544768 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0484. Min Act: -0.0002

Data Index: 295434 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0458. Min Act: -0.0002

Data Index: 771085 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0480. Min Act: -0.0002

Data Index: 709873 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0443. Min Act: -0.0002

Data Index: 348737 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1126026 (C4 (Web Text))

Max Activating Token Index: 646