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

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

Neuron 86 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: 2.5916. Min Range: -2.5916

Max Act: 2.5408. Min Act: -0.0000

Data Index: 823846 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 2.5916. Min Range: -2.5916

Max Act: 2.5916. Min Act: -0.0000

Data Index: 844746 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 2.5916. Min Range: -2.5916

Max Act: 2.2898. Min Act: -0.0000

Data Index: 775079 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 2.5916. Min Range: -2.5916

Max Act: 2.2799. Min Act: -0.0000

Data Index: 875899 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.9629. Min Act: -0.0000

Data Index: 581396 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.5916. Min Range: -2.5916

Max Act: 2.1686. Min Act: -0.0000

Data Index: 552394 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.9256. Min Act: -0.0000

Data Index: 935382 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.8879. Min Act: -0.0000

Data Index: 1322353 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.9961. Min Act: -0.0000

Data Index: 591576 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.7654. Min Act: -0.0000

Data Index: 768087 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.9020. Min Act: -0.0000

Data Index: 837321 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.8135. Min Act: -0.0000

Data Index: 496032 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.7901. Min Act: -0.0000

Data Index: 1104197 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.7771. Min Act: -0.0000

Data Index: 29161 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.8627. Min Act: -0.0000

Data Index: 754946 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.7657. Min Act: -0.0000

Data Index: 436977 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.8507. Min Act: -0.0000

Data Index: 141571 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.6388. Min Act: -0.0000

Data Index: 852787 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.8414. Min Act: -0.0000

Data Index: 448218 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 2.5916. Min Range: -2.5916

Max Act: 1.8077. Min Act: -0.0000

Data Index: 1031010 (C4 (Web Text))

Max Activating Token Index: 47