Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2160 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.6105. Min Act: -0.0000

Data Index: 1134666 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 3.6105. Min Range: -3.6105

Max Act: 3.1762. Min Act: -0.0000

Data Index: 789974 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.7650. Min Act: -0.0000

Data Index: 383358 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.7057. Min Act: -0.0000

Data Index: 573554 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.6759. Min Act: -0.0000

Data Index: 413780 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.4953. Min Act: -0.0000

Data Index: 180942 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.3548. Min Act: -0.0000

Data Index: 470049 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.4712. Min Act: -0.0000

Data Index: 996061 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.3357. Min Act: -0.0000

Data Index: 35878 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.5870. Min Act: -0.0000

Data Index: 413025 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.4335. Min Act: -0.0000

Data Index: 592265 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.4302. Min Act: -0.0000

Data Index: 400247 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.4187. Min Act: -0.0000

Data Index: 941301 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.3625. Min Act: -0.0000

Data Index: 779547 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.2221. Min Act: -0.0000

Data Index: 130501 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.2896. Min Act: -0.0000

Data Index: 673230 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.1729. Min Act: -0.0000

Data Index: 1030436 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.2916. Min Act: -0.0000

Data Index: 48882 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.2273. Min Act: -0.0000

Data Index: 736086 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 3.6105. Min Range: -3.6105

Max Act: 2.2083. Min Act: -0.0000

Data Index: 532464 (C4 (Web Text))

Max Activating Token Index: 160