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

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

Neuron 4625 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2978. Min Range: -2.2978

Max Act: 2.2978. Min Act: -0.0000

Data Index: 403945 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 2.2978. Min Range: -2.2978

Max Act: 2.2213. Min Act: -0.0000

Data Index: 1648309 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.9381. Min Act: -0.0000

Data Index: 1541325 (Python Code)

Max Activating Token Index: 703

Text #3

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.8567. Min Act: -0.0000

Data Index: 1629068 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.8427. Min Act: -0.0000

Data Index: 1439526 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.7389. Min Act: -0.0000

Data Index: 1624935 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.6965. Min Act: -0.0000

Data Index: 1450975 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1439104 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1382506 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.8357. Min Act: -0.0000

Data Index: 1432917 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.7253. Min Act: -0.0000

Data Index: 1605780 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1502305 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.6920. Min Act: -0.0000

Data Index: 1535729 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1588601 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.6644. Min Act: -0.0000

Data Index: 1616578 (Python Code)

Max Activating Token Index: 759

Text #15

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1393726 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1589069 (Python Code)

Max Activating Token Index: 679

Text #17

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.6471. Min Act: -0.0000

Data Index: 1432837 (Python Code)

Max Activating Token Index: 859

Text #18

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.5869. Min Act: -0.0000

Data Index: 547920 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 2.2978. Min Range: -2.2978

Max Act: 1.5732. Min Act: -0.0000

Data Index: 1439333 (Python Code)

Max Activating Token Index: 973