Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2949 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.6851. Min Act: -0.0002

Data Index: 519254 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.6643. Min Act: -0.0001

Data Index: 908147 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.6026. Min Act: -0.0001

Data Index: 1092544 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5640. Min Act: -0.0002

Data Index: 739361 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5685. Min Act: -0.0002

Data Index: 1330526 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5649. Min Act: -0.0002

Data Index: 1158387 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5551. Min Act: -0.0002

Data Index: 835733 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5773. Min Act: -0.0001

Data Index: 375673 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5289. Min Act: -0.0002

Data Index: 740045 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5437. Min Act: -0.0002

Data Index: 1056536 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5381. Min Act: -0.0002

Data Index: 87171 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5562. Min Act: -0.0001

Data Index: 335777 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5368. Min Act: -0.0002

Data Index: 1216721 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5336. Min Act: -0.0002

Data Index: 483999 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5287. Min Act: -0.0002

Data Index: 201800 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5151. Min Act: -0.0002

Data Index: 261274 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5335. Min Act: -0.0002

Data Index: 928238 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5122. Min Act: -0.0001

Data Index: 76893 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5082. Min Act: -0.0001

Data Index: 1302988 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5438. Min Act: -0.0001

Data Index: 390047 (C4 (Web Text))

Max Activating Token Index: 1003