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

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

Neuron 3911 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3366. Min Range: -3.3366

Max Act: 3.2084. Min Act: -0.0000

Data Index: 1477608 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 3.3366. Min Range: -3.3366

Max Act: 3.2889. Min Act: -0.0000

Data Index: 570242 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.3366. Min Range: -3.3366

Max Act: 3.1426. Min Act: -0.0000

Data Index: 709615 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 3.3366. Min Range: -3.3366

Max Act: 3.3366. Min Act: -0.0000

Data Index: 1294707 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.8552. Min Act: -0.0000

Data Index: 332602 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.9837. Min Act: -0.0000

Data Index: 1548296 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 3.3366. Min Range: -3.3366

Max Act: 3.0994. Min Act: -0.0000

Data Index: 552473 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.8144. Min Act: -0.0000

Data Index: 817412 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.7787. Min Act: -0.0000

Data Index: 227344 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.9120. Min Act: -0.0000

Data Index: 1208528 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 3.3366. Min Range: -3.3366

Max Act: 3.1652. Min Act: -0.0000

Data Index: 99027 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.7608. Min Act: -0.0000

Data Index: 824323 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.7133. Min Act: -0.0000

Data Index: 1073887 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.6879. Min Act: -0.0000

Data Index: 26951 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.9446. Min Act: -0.0000

Data Index: 1350529 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.8057. Min Act: -0.0000

Data Index: 1498352 (Python Code)

Max Activating Token Index: 840

Text #16

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.8065. Min Act: -0.0000

Data Index: 762934 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.7858. Min Act: -0.0000

Data Index: 1596242 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.7811. Min Act: -0.0000

Data Index: 180732 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 3.3366. Min Range: -3.3366

Max Act: 2.7579. Min Act: -0.0000

Data Index: 641327 (C4 (Web Text))

Max Activating Token Index: 28