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

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

Neuron 60 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.7849. Min Act: -0.0000

Data Index: 808746 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.6104. Min Act: -0.0000

Data Index: 1281681 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.5372. Min Act: -0.0000

Data Index: 658739 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.4491. Min Act: -0.0000

Data Index: 1305022 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.3454. Min Act: -0.0000

Data Index: 147573 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.3714. Min Act: -0.0000

Data Index: 107034 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.2360. Min Act: -0.0000

Data Index: 98601 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.3558. Min Act: -0.0000

Data Index: 8478 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.2983. Min Act: -0.0000

Data Index: 482201 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1058204 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.1446. Min Act: -0.0000

Data Index: 604561 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.1249. Min Act: -0.0000

Data Index: 862810 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 1.7849. Min Range: -1.7849

Max Act: 0.9105. Min Act: -0.0000

Data Index: 371488 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1071519 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.0448. Min Act: -0.0000

Data Index: 2452 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.7849. Min Range: -1.7849

Max Act: 0.9953. Min Act: -0.0000

Data Index: 330346 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.0743. Min Act: -0.0000

Data Index: 777333 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.0692. Min Act: -0.0000

Data Index: 271415 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.0946. Min Act: -0.0000

Data Index: 524374 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 1.7849. Min Range: -1.7849

Max Act: 1.0423. Min Act: -0.0000

Data Index: 534065 (C4 (Web Text))

Max Activating Token Index: 193