Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 905 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8499. Min Act: -0.0001

Data Index: 846445 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8248. Min Act: -0.0001

Data Index: 725889 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1266404 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8049. Min Act: -0.0000

Data Index: 787283 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7451. Min Act: -0.0001

Data Index: 538750 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6869. Min Act: -0.0000

Data Index: 141944 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6889. Min Act: -0.0000

Data Index: 394893 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7035. Min Act: -0.0001

Data Index: 1027345 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6781. Min Act: -0.0001

Data Index: 624515 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1165653 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6618. Min Act: -0.0000

Data Index: 955958 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6415. Min Act: -0.0000

Data Index: 279246 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6641. Min Act: -0.0001

Data Index: 1177519 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6324. Min Act: -0.0000

Data Index: 779249 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1345791 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1046029 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6344. Min Act: -0.0001

Data Index: 662151 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6341. Min Act: -0.0001

Data Index: 705459 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1320871 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6466. Min Act: -0.0001

Data Index: 438254 (C4 (Web Text))

Max Activating Token Index: 113