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

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

Neuron 4772 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: 1.4916. Min Range: -1.4916

Max Act: 1.4916. Min Act: -0.0000

Data Index: 990530 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.4916. Min Range: -1.4916

Max Act: 1.0900. Min Act: -0.0000

Data Index: 771742 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1252524 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.9135. Min Act: -0.0000

Data Index: 409849 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8507. Min Act: -0.0000

Data Index: 977788 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8603. Min Act: -0.0000

Data Index: 936418 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8920. Min Act: -0.0000

Data Index: 220397 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8903. Min Act: -0.0000

Data Index: 485041 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8879. Min Act: -0.0000

Data Index: 735752 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1063598 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1207332 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8401. Min Act: -0.0000

Data Index: 780956 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1310280 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.9485. Min Act: -0.0000

Data Index: 725423 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8466. Min Act: -0.0000

Data Index: 101066 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.7270. Min Act: -0.0000

Data Index: 117178 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8033. Min Act: -0.0000

Data Index: 122913 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.7821. Min Act: -0.0000

Data Index: 93526 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1556816 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 1.4916. Min Range: -1.4916

Max Act: 0.8191. Min Act: -0.0000

Data Index: 499578 (C4 (Web Text))

Max Activating Token Index: 740