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

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

Neuron 5665 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0290. Min Range: -3.0290

Max Act: 3.0088. Min Act: -0.0000

Data Index: 443080 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 3.0290. Min Range: -3.0290

Max Act: 3.0290. Min Act: -0.0000

Data Index: 921797 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.9019. Min Act: -0.0000

Data Index: 427522 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.9141. Min Act: -0.0000

Data Index: 617301 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.7592. Min Act: -0.0000

Data Index: 1094965 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.7152. Min Act: -0.0000

Data Index: 1014918 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.9396. Min Act: -0.0000

Data Index: 615736 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.7797. Min Act: -0.0000

Data Index: 296933 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.5126. Min Act: -0.0000

Data Index: 46050 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.3043. Min Act: -0.0000

Data Index: 592863 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.6939. Min Act: -0.0000

Data Index: 1303366 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.3012. Min Act: -0.0000

Data Index: 247411 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.4152. Min Act: -0.0000

Data Index: 657220 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.2553. Min Act: -0.0000

Data Index: 221414 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.1607. Min Act: -0.0000

Data Index: 105632 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.5290. Min Act: -0.0000

Data Index: 802382 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.8614. Min Act: -0.0000

Data Index: 706306 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.4575. Min Act: -0.0000

Data Index: 1039755 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.2046. Min Act: -0.0000

Data Index: 11321 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 3.0290. Min Range: -3.0290

Max Act: 2.3462. Min Act: -0.0000

Data Index: 445433 (C4 (Web Text))

Max Activating Token Index: 845