Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1952 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1551572 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 1.3404. Min Range: -1.3404

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1414263 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1596550 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1514872 (Python Code)

Max Activating Token Index: 773

Text #4

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1467413 (Python Code)

Max Activating Token Index: 215

Text #5

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1474995 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1398356 (Python Code)

Max Activating Token Index: 179

Text #7

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1529435 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1428314 (Python Code)

Max Activating Token Index: 790

Text #9

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1391442 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1551168 (Python Code)

Max Activating Token Index: 881

Text #11

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1394428 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1456573 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1645160 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1479696 (Python Code)

Max Activating Token Index: 441

Text #15

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1619882 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1479966 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1414300 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1526563 (Python Code)

Max Activating Token Index: 402

Text #19

Max Range: 1.3404. Min Range: -1.3404

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1495933 (Python Code)

Max Activating Token Index: 956