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

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

Neuron 5379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7472. Min Range: -5.7472

Max Act: 5.7472. Min Act: -0.0001

Data Index: 684519 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 5.7472. Min Range: -5.7472

Max Act: 4.2949. Min Act: -0.0001

Data Index: 463779 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 5.7472. Min Range: -5.7472

Max Act: 4.9853. Min Act: -0.0001

Data Index: 581550 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 5.7472. Min Range: -5.7472

Max Act: 4.0619. Min Act: -0.0001

Data Index: 1163490 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.7185. Min Act: -0.0001

Data Index: 111552 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.1022. Min Act: -0.0001

Data Index: 932882 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.4324. Min Act: -0.0001

Data Index: 886472 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.5146. Min Act: -0.0001

Data Index: 1352736 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.6711. Min Act: -0.0001

Data Index: 688225 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.8381. Min Act: -0.0001

Data Index: 188111 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 5.7472. Min Range: -5.7472

Max Act: 4.1641. Min Act: -0.0001

Data Index: 107758 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.7769. Min Act: -0.0001

Data Index: 1508199 (Python Code)

Max Activating Token Index: 313

Text #12

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.6996. Min Act: -0.0001

Data Index: 1274688 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.7172. Min Act: -0.0001

Data Index: 732982 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.8847. Min Act: -0.0001

Data Index: 1161837 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.6764. Min Act: -0.0001

Data Index: 923408 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.2473. Min Act: -0.0001

Data Index: 1028581 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.3907. Min Act: -0.0001

Data Index: 105415 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.3295. Min Act: -0.0001

Data Index: 693279 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 5.7472. Min Range: -5.7472

Max Act: 3.4815. Min Act: -0.0001

Data Index: 582256 (C4 (Web Text))

Max Activating Token Index: 208