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

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

Neuron 1662 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: 0.4669. Min Range: -0.4669

Max Act: 0.4669. Min Act: -0.0001

Data Index: 1177770 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.4631. Min Act: -0.0001

Data Index: 884894 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3857. Min Act: -0.0001

Data Index: 1088246 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3889. Min Act: -0.0001

Data Index: 197213 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3647. Min Act: -0.0001

Data Index: 428861 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3447. Min Act: -0.0001

Data Index: 1082787 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3314. Min Act: -0.0001

Data Index: 821223 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2803. Min Act: -0.0001

Data Index: 1543271 (Python Code)

Max Activating Token Index: 682

Text #8

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3021. Min Act: -0.0001

Data Index: 910477 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2721. Min Act: -0.0001

Data Index: 1361793 (Python Code)

Max Activating Token Index: 69

Text #10

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2409. Min Act: -0.0001

Data Index: 1123357 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1384325 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1423151 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1421235 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1440859 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1386170 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1379919 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1388535 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1429855 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1399842 (Python Code)

Max Activating Token Index: 4