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

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

Neuron 3003 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: 4.0664. Min Range: -4.0664

Max Act: 4.0664. Min Act: -0.0000

Data Index: 873203 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.7258. Min Act: -0.0000

Data Index: 754454 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.4336. Min Act: -0.0000

Data Index: 2831 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.4153. Min Act: -0.0000

Data Index: 988714 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.3796. Min Act: -0.0000

Data Index: 140744 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.5257. Min Act: -0.0000

Data Index: 1282980 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.4679. Min Act: -0.0000

Data Index: 627333 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.5953. Min Act: -0.0000

Data Index: 783086 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.3789. Min Act: -0.0000

Data Index: 1069687 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.3371. Min Act: -0.0000

Data Index: 782838 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.4610. Min Act: -0.0000

Data Index: 1055455 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.1375. Min Act: -0.0000

Data Index: 990921 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.2291. Min Act: -0.0000

Data Index: 422173 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.2275. Min Act: -0.0000

Data Index: 429121 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.2126. Min Act: -0.0000

Data Index: 786619 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.2139. Min Act: -0.0000

Data Index: 451317 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.1956. Min Act: -0.0001

Data Index: 764760 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.0015. Min Act: -0.0000

Data Index: 1240875 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.1277. Min Act: -0.0000

Data Index: 984516 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 4.0664. Min Range: -4.0664

Max Act: 3.2686. Min Act: -0.0000

Data Index: 675091 (C4 (Web Text))

Max Activating Token Index: 777