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

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

Neuron 1620 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3873. Min Range: -4.3873

Max Act: 4.2759. Min Act: -0.0000

Data Index: 1150237 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 4.3873. Min Range: -4.3873

Max Act: 4.2105. Min Act: -0.0000

Data Index: 1180206 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 4.3873. Min Range: -4.3873

Max Act: 4.3873. Min Act: -0.0000

Data Index: 1203487 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 4.3873. Min Range: -4.3873

Max Act: 3.9814. Min Act: -0.0000

Data Index: 171311 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 4.3873. Min Range: -4.3873

Max Act: 4.0194. Min Act: -0.0000

Data Index: 145702 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 4.3873. Min Range: -4.3873

Max Act: 2.3374. Min Act: -0.0000

Data Index: 149696 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 4.3873. Min Range: -4.3873

Max Act: 2.0770. Min Act: -0.0000

Data Index: 1477688 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 4.3873. Min Range: -4.3873

Max Act: 2.1905. Min Act: -0.0000

Data Index: 1493109 (Python Code)

Max Activating Token Index: 202

Text #8

Max Range: 4.3873. Min Range: -4.3873

Max Act: 2.2052. Min Act: -0.0000

Data Index: 1511939 (Python Code)

Max Activating Token Index: 254

Text #9

Max Range: 4.3873. Min Range: -4.3873

Max Act: 2.0861. Min Act: -0.0000

Data Index: 1653955 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 4.3873. Min Range: -4.3873

Max Act: 2.0158. Min Act: -0.0000

Data Index: 1369563 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 4.3873. Min Range: -4.3873

Max Act: 2.0110. Min Act: -0.0000

Data Index: 1542375 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 4.3873. Min Range: -4.3873

Max Act: 2.3086. Min Act: -0.0000

Data Index: 1494916 (Python Code)

Max Activating Token Index: 378

Text #13

Max Range: 4.3873. Min Range: -4.3873

Max Act: 1.9829. Min Act: -0.0000

Data Index: 1535842 (Python Code)

Max Activating Token Index: 721

Text #14

Max Range: 4.3873. Min Range: -4.3873

Max Act: 1.7586. Min Act: -0.0000

Data Index: 312493 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 4.3873. Min Range: -4.3873

Max Act: 1.4729. Min Act: -0.0000

Data Index: 785481 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 4.3873. Min Range: -4.3873

Max Act: 1.5330. Min Act: -0.0000

Data Index: 1427970 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 4.3873. Min Range: -4.3873

Max Act: 1.5429. Min Act: -0.0000

Data Index: 428924 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 4.3873. Min Range: -4.3873

Max Act: 1.5825. Min Act: -0.0000

Data Index: 561181 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 4.3873. Min Range: -4.3873

Max Act: 1.4443. Min Act: -0.0000

Data Index: 910388 (C4 (Web Text))

Max Activating Token Index: 780