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

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

Neuron 2063 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.7883. Min Act: -0.0000

Data Index: 1517640 (Python Code)

Max Activating Token Index: 812

Text #1

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.7655. Min Act: -0.0000

Data Index: 1539980 (Python Code)

Max Activating Token Index: 697

Text #2

Max Range: 3.7883. Min Range: -3.7883

Max Act: 3.0992. Min Act: -0.0000

Data Index: 1563915 (Python Code)

Max Activating Token Index: 253

Text #3

Max Range: 3.7883. Min Range: -3.7883

Max Act: 2.2265. Min Act: -0.0000

Data Index: 956836 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 3.7883. Min Range: -3.7883

Max Act: 2.0587. Min Act: -0.0000

Data Index: 769884 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 3.7883. Min Range: -3.7883

Max Act: 2.0158. Min Act: -0.0000

Data Index: 531119 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.8597. Min Act: -0.0000

Data Index: 255792 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 3.7883. Min Range: -3.7883

Max Act: 2.1150. Min Act: -0.0000

Data Index: 349043 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.8026. Min Act: -0.0000

Data Index: 1593225 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.8101. Min Act: -0.0000

Data Index: 1615439 (Python Code)

Max Activating Token Index: 141

Text #10

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.7732. Min Act: -0.0000

Data Index: 311535 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.7324. Min Act: -0.0000

Data Index: 929399 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.6365. Min Act: -0.0000

Data Index: 640804 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.6316. Min Act: -0.0000

Data Index: 783214 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.6110. Min Act: -0.0000

Data Index: 465825 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.6069. Min Act: -0.0000

Data Index: 518828 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.5365. Min Act: -0.0000

Data Index: 60062 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1621099 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.5354. Min Act: -0.0000

Data Index: 1526662 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 3.7883. Min Range: -3.7883

Max Act: 1.4949. Min Act: -0.0000

Data Index: 1197586 (C4 (Web Text))

Max Activating Token Index: 626