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

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

Neuron 3474 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.5931. Min Act: -0.0000

Data Index: 768790 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.3929. Min Act: -0.0000

Data Index: 660462 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.3560. Min Act: -0.0000

Data Index: 844126 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.1339. Min Act: -0.0000

Data Index: 297847 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.0898. Min Act: -0.0000

Data Index: 605512 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.2336. Min Act: -0.0000

Data Index: 589813 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.1828. Min Act: -0.0000

Data Index: 520243 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.0040. Min Act: -0.0000

Data Index: 1158955 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.8882. Min Act: -0.0000

Data Index: 1107301 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.0661. Min Act: -0.0000

Data Index: 214354 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.8492. Min Act: -0.0000

Data Index: 458641 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.8365. Min Act: -0.0000

Data Index: 1083225 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.8604. Min Act: -0.0000

Data Index: 396926 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.6905. Min Act: -0.0000

Data Index: 308837 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.0250. Min Act: -0.0000

Data Index: 494872 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 4.5931. Min Range: -4.5931

Max Act: 4.0352. Min Act: -0.0000

Data Index: 642662 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.6531. Min Act: -0.0000

Data Index: 1055013 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.7210. Min Act: -0.0000

Data Index: 379543 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.8993. Min Act: -0.0000

Data Index: 424226 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 4.5931. Min Range: -4.5931

Max Act: 3.6599. Min Act: -0.0000

Data Index: 360178 (C4 (Web Text))

Max Activating Token Index: 63