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

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

Neuron 676 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0434. Min Act: -0.0001

Data Index: 499843 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.2050. Min Act: -0.0000

Data Index: 503643 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0381. Min Act: -0.0000

Data Index: 655897 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9158. Min Act: -0.0001

Data Index: 398879 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.9047. Min Act: -0.0000

Data Index: 1285853 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0774. Min Act: -0.0001

Data Index: 905076 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 3.2050. Min Range: -3.2050

Max Act: 3.0535. Min Act: -0.0001

Data Index: 920663 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.2111. Min Act: -0.0001

Data Index: 144449 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.1035. Min Act: -0.0000

Data Index: 1147416 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.9346. Min Act: -0.0001

Data Index: 803241 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.8419. Min Act: -0.0001

Data Index: 516675 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.9475. Min Act: -0.0000

Data Index: 314644 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.9560. Min Act: -0.0000

Data Index: 856353 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 3.2050. Min Range: -3.2050

Max Act: 2.0546. Min Act: -0.0001

Data Index: 887729 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.8022. Min Act: -0.0000

Data Index: 1091727 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.7970. Min Act: -0.0001

Data Index: 1246904 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.7960. Min Act: -0.0001

Data Index: 1089103 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.6556. Min Act: -0.0000

Data Index: 865990 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.6421. Min Act: -0.0000

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 3.2050. Min Range: -3.2050

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1000698 (C4 (Web Text))

Max Activating Token Index: 1008