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

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

Neuron 4255 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: 1.6286. Min Range: -1.6286

Max Act: 1.6286. Min Act: -0.0001

Data Index: 211772 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.3217. Min Act: -0.0001

Data Index: 1250430 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.4300. Min Act: -0.0001

Data Index: 238411 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.2944. Min Act: -0.0001

Data Index: 194081 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.2718. Min Act: -0.0001

Data Index: 1013449 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.3416. Min Act: -0.0001

Data Index: 19079 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.2157. Min Act: -0.0001

Data Index: 734140 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.1848. Min Act: -0.0001

Data Index: 1188955 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.1719. Min Act: -0.0001

Data Index: 705411 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.1081. Min Act: -0.0001

Data Index: 1103874 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.1672. Min Act: -0.0001

Data Index: 454646 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.1434. Min Act: -0.0001

Data Index: 952244 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.0805. Min Act: -0.0001

Data Index: 674328 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.6286. Min Range: -1.6286

Max Act: 1.0533. Min Act: -0.0001

Data Index: 944513 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.6286. Min Range: -1.6286

Max Act: 0.9918. Min Act: -0.0001

Data Index: 1355751 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.6286. Min Range: -1.6286

Max Act: 0.9952. Min Act: -0.0001

Data Index: 910983 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.6286. Min Range: -1.6286

Max Act: 0.9387. Min Act: -0.0001

Data Index: 73920 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 1.6286. Min Range: -1.6286

Max Act: 0.8818. Min Act: -0.0001

Data Index: 354039 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 1.6286. Min Range: -1.6286

Max Act: 0.9902. Min Act: -0.0001

Data Index: 171592 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 1.6286. Min Range: -1.6286

Max Act: 0.9586. Min Act: -0.0001

Data Index: 245929 (C4 (Web Text))

Max Activating Token Index: 1013