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

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

Neuron 1764 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4916. Min Range: -4.4916

Max Act: 4.4916. Min Act: -0.0000

Data Index: 184979 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 4.4916. Min Range: -4.4916

Max Act: 3.9135. Min Act: -0.0000

Data Index: 385709 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 4.4916. Min Range: -4.4916

Max Act: 3.2947. Min Act: -0.0000

Data Index: 837932 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 4.4916. Min Range: -4.4916

Max Act: 3.6663. Min Act: -0.0000

Data Index: 1295953 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 4.4916. Min Range: -4.4916

Max Act: 3.5338. Min Act: -0.0000

Data Index: 92176 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 4.4916. Min Range: -4.4916

Max Act: 3.2500. Min Act: -0.0000

Data Index: 1333395 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 4.4916. Min Range: -4.4916

Max Act: 3.0682. Min Act: -0.0000

Data Index: 855321 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 4.4916. Min Range: -4.4916

Max Act: 3.0229. Min Act: -0.0000

Data Index: 940099 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.9525. Min Act: -0.0000

Data Index: 64359 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.8950. Min Act: -0.0000

Data Index: 748884 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.6557. Min Act: -0.0000

Data Index: 664790 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 4.4916. Min Range: -4.4916

Max Act: 3.5540. Min Act: -0.0000

Data Index: 1211851 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.8645. Min Act: -0.0000

Data Index: 584008 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.8594. Min Act: -0.0000

Data Index: 999011 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.8175. Min Act: -0.0000

Data Index: 1352548 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.7818. Min Act: -0.0000

Data Index: 734636 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.8779. Min Act: -0.0000

Data Index: 417695 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.5874. Min Act: -0.0000

Data Index: 254450 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.5525. Min Act: 0.0000

Data Index: 659551 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 4.4916. Min Range: -4.4916

Max Act: 2.8891. Min Act: -0.0000

Data Index: 386434 (C4 (Web Text))

Max Activating Token Index: 897