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

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

Neuron 4256 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: 2.6582. Min Range: -2.6582

Max Act: 2.6582. Min Act: -0.0000

Data Index: 854612 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 2.6582. Min Range: -2.6582

Max Act: 2.4134. Min Act: -0.0000

Data Index: 1369693 (Python Code)

Max Activating Token Index: 425

Text #2

Max Range: 2.6582. Min Range: -2.6582

Max Act: 2.5718. Min Act: -0.0000

Data Index: 804262 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 2.6582. Min Range: -2.6582

Max Act: 2.2084. Min Act: -0.0000

Data Index: 957629 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 2.6582. Min Range: -2.6582

Max Act: 2.0854. Min Act: -0.0000

Data Index: 739936 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 2.6582. Min Range: -2.6582

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1557388 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.9974. Min Act: -0.0000

Data Index: 829945 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.9566. Min Act: -0.0000

Data Index: 971331 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.8641. Min Act: -0.0000

Data Index: 1112413 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.8523. Min Act: -0.0000

Data Index: 228790 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.8414. Min Act: -0.0000

Data Index: 441958 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.7936. Min Act: -0.0000

Data Index: 155162 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.8048. Min Act: -0.0000

Data Index: 313899 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.6686. Min Act: -0.0000

Data Index: 1022624 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.6478. Min Act: -0.0000

Data Index: 1344841 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.7495. Min Act: -0.0000

Data Index: 330673 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1029229 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.6133. Min Act: -0.0000

Data Index: 919832 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.6019. Min Act: -0.0000

Data Index: 1277005 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 2.6582. Min Range: -2.6582

Max Act: 1.5898. Min Act: -0.0000

Data Index: 934803 (C4 (Web Text))

Max Activating Token Index: 349