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

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

Neuron 4720 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: 3.1099. Min Range: -3.1099

Max Act: 3.1099. Min Act: -0.0000

Data Index: 189931 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.7874. Min Act: -0.0000

Data Index: 583959 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 3.1099. Min Range: -3.1099

Max Act: 3.0464. Min Act: -0.0000

Data Index: 520250 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.9306. Min Act: -0.0000

Data Index: 663985 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.8583. Min Act: -0.0000

Data Index: 1129023 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.7645. Min Act: -0.0000

Data Index: 486026 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.7366. Min Act: -0.0000

Data Index: 173908 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.5666. Min Act: -0.0000

Data Index: 709109 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.5407. Min Act: -0.0000

Data Index: 341118 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.4912. Min Act: -0.0000

Data Index: 968613 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.7217. Min Act: -0.0000

Data Index: 375911 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.6781. Min Act: -0.0000

Data Index: 835932 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.2842. Min Act: -0.0000

Data Index: 333929 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.5236. Min Act: -0.0000

Data Index: 607912 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.5133. Min Act: -0.0000

Data Index: 1321775 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.4964. Min Act: -0.0000

Data Index: 1296300 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.6003. Min Act: -0.0000

Data Index: 925058 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.4620. Min Act: -0.0000

Data Index: 809770 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.3270. Min Act: -0.0000

Data Index: 983405 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 3.1099. Min Range: -3.1099

Max Act: 2.4525. Min Act: -0.0000

Data Index: 33066 (C4 (Web Text))

Max Activating Token Index: 35