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

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

Neuron 4060 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: 1.6562. Min Range: -1.6562

Max Act: 1.6562. Min Act: -0.0002

Data Index: 637899 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.3872. Min Act: -0.0002

Data Index: 1108397 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.1280. Min Act: -0.0002

Data Index: 1263989 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.4373. Min Act: -0.0002

Data Index: 223967 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.3932. Min Act: -0.0002

Data Index: 882104 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.3782. Min Act: -0.0002

Data Index: 561852 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.2641. Min Act: -0.0002

Data Index: 172523 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.1436. Min Act: -0.0002

Data Index: 231980 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.2831. Min Act: -0.0002

Data Index: 396024 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.3348. Min Act: -0.0002

Data Index: 7596 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.2686. Min Act: -0.0002

Data Index: 689862 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.4058. Min Act: -0.0002

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.0935. Min Act: -0.0002

Data Index: 849020 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.1320. Min Act: -0.0002

Data Index: 1354301 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.3626. Min Act: -0.0002

Data Index: 913318 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.0174. Min Act: -0.0002

Data Index: 650804 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.2106. Min Act: -0.0002

Data Index: 940198 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.1428. Min Act: -0.0002

Data Index: 1144564 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.1995. Min Act: -0.0002

Data Index: 518869 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 1.6562. Min Range: -1.6562

Max Act: 1.3078. Min Act: -0.0002

Data Index: 547587 (C4 (Web Text))

Max Activating Token Index: 884