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

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

Neuron 1603 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: 3.7763. Min Range: -3.7763

Max Act: 3.7763. Min Act: -0.0000

Data Index: 1515894 (Python Code)

Max Activating Token Index: 809

Text #1

Max Range: 3.7763. Min Range: -3.7763

Max Act: 3.6898. Min Act: -0.0000

Data Index: 1478908 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 3.7763. Min Range: -3.7763

Max Act: 3.4481. Min Act: -0.0000

Data Index: 1315371 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.9594. Min Act: -0.0000

Data Index: 1414964 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 3.7763. Min Range: -3.7763

Max Act: 3.0519. Min Act: -0.0000

Data Index: 887111 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.9964. Min Act: -0.0000

Data Index: 952259 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.9337. Min Act: -0.0000

Data Index: 194368 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.8807. Min Act: -0.0000

Data Index: 1556738 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.4758. Min Act: -0.0000

Data Index: 1415590 (Python Code)

Max Activating Token Index: 831

Text #9

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.5569. Min Act: -0.0000

Data Index: 417333 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.5284. Min Act: -0.0000

Data Index: 797811 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.9176. Min Act: -0.0000

Data Index: 1079924 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.5198. Min Act: -0.0000

Data Index: 1004899 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.7794. Min Act: -0.0000

Data Index: 86082 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.1205. Min Act: -0.0000

Data Index: 1267489 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.5759. Min Act: -0.0000

Data Index: 1395309 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.3251. Min Act: -0.0000

Data Index: 823422 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.5059. Min Act: -0.0000

Data Index: 1593683 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.1403. Min Act: -0.0000

Data Index: 1462934 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 3.7763. Min Range: -3.7763

Max Act: 2.3676. Min Act: -0.0000

Data Index: 703738 (C4 (Web Text))

Max Activating Token Index: 78