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

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

Neuron 4080 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.4093. Min Act: -0.0000

Data Index: 229654 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.3672. Min Act: -0.0000

Data Index: 987019 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1293078 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.3274. Min Act: -0.0000

Data Index: 762524 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.3096. Min Act: -0.0000

Data Index: 693545 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2961. Min Act: -0.0000

Data Index: 601941 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.3033. Min Act: -0.0000

Data Index: 834366 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2879. Min Act: -0.0000

Data Index: 492785 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2816. Min Act: -0.0000

Data Index: 514061 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2868. Min Act: -0.0000

Data Index: 941293 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2843. Min Act: -0.0000

Data Index: 711075 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1134304 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2939. Min Act: -0.0000

Data Index: 257017 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2572. Min Act: -0.0000

Data Index: 703543 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2857. Min Act: -0.0000

Data Index: 1221485 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2748. Min Act: -0.0000

Data Index: 375017 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1058035 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2800. Min Act: -0.0001

Data Index: 147517 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2990. Min Act: -0.0000

Data Index: 184238 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.4093. Min Range: -0.4093

Max Act: 0.2889. Min Act: -0.0000

Data Index: 319070 (C4 (Web Text))

Max Activating Token Index: 246