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

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

Neuron 1702 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.9153. Min Act: -0.0001

Data Index: 144878 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.9161. Min Act: -0.0001

Data Index: 1359779 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 4.1865. Min Range: -4.1865

Max Act: 4.1865. Min Act: -0.0001

Data Index: 828468 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.6943. Min Act: -0.0001

Data Index: 691089 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.7535. Min Act: -0.0001

Data Index: 91943 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.5325. Min Act: -0.0001

Data Index: 1129258 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.1046. Min Act: -0.0001

Data Index: 858689 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.5345. Min Act: -0.0001

Data Index: 32524 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.1307. Min Act: -0.0001

Data Index: 712382 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.2849. Min Act: -0.0001

Data Index: 285066 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.3604. Min Act: -0.0001

Data Index: 1219493 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.1612. Min Act: -0.0001

Data Index: 37249 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.1411. Min Act: -0.0001

Data Index: 800077 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 4.1865. Min Range: -4.1865

Max Act: 2.9562. Min Act: -0.0001

Data Index: 80823 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.0592. Min Act: -0.0001

Data Index: 731594 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.0418. Min Act: -0.0001

Data Index: 570868 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 4.1865. Min Range: -4.1865

Max Act: 2.9011. Min Act: -0.0001

Data Index: 583213 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.1407. Min Act: -0.0001

Data Index: 974873 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.0139. Min Act: -0.0001

Data Index: 424177 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 4.1865. Min Range: -4.1865

Max Act: 2.9971. Min Act: -0.0001

Data Index: 170826 (C4 (Web Text))

Max Activating Token Index: 647