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

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

Neuron 964 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1003366 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3975. Min Act: -0.0000

Data Index: 198681 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1597856 (Python Code)

Max Activating Token Index: 769

Text #3

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1451595 (Python Code)

Max Activating Token Index: 172

Text #4

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3965. Min Act: -0.0000

Data Index: 40356 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3949. Min Act: -0.0000

Data Index: 805787 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1304152 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3916. Min Act: -0.0000

Data Index: 87480 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4044. Min Act: -0.0000

Data Index: 387129 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1611553 (Python Code)

Max Activating Token Index: 684

Text #10

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1508838 (Python Code)

Max Activating Token Index: 549

Text #11

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1550261 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1466798 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3728. Min Act: -0.0000

Data Index: 803031 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3566. Min Act: -0.0000

Data Index: 285165 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1028448 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3431. Min Act: -0.0000

Data Index: 176307 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1616795 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3507. Min Act: -0.0000

Data Index: 607906 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.3331. Min Act: -0.0000

Data Index: 289868 (C4 (Web Text))

Max Activating Token Index: 479