Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 259 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.8766. Min Act: -0.0001

Data Index: 1592410 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.8038. Min Act: -0.0001

Data Index: 536419 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7684. Min Act: -0.0001

Data Index: 1574771 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7671. Min Act: -0.0001

Data Index: 1361145 (Python Code)

Max Activating Token Index: 492

Text #4

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7185. Min Act: -0.0001

Data Index: 1656381 (Python Code)

Max Activating Token Index: 914

Text #5

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6780. Min Act: -0.0001

Data Index: 813207 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7291. Min Act: -0.0001

Data Index: 1291692 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7024. Min Act: -0.0001

Data Index: 1464263 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7548. Min Act: -0.0001

Data Index: 1382278 (Python Code)

Max Activating Token Index: 962

Text #9

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7065. Min Act: -0.0001

Data Index: 1533068 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6889. Min Act: -0.0001

Data Index: 1250076 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6678. Min Act: -0.0001

Data Index: 888383 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6877. Min Act: -0.0001

Data Index: 528883 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6873. Min Act: -0.0001

Data Index: 1218513 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6919. Min Act: -0.0001

Data Index: 657141 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.7116. Min Act: -0.0001

Data Index: 1111067 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6884. Min Act: -0.0001

Data Index: 912746 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6426. Min Act: -0.0001

Data Index: 435258 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6777. Min Act: -0.0001

Data Index: 439648 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.8766. Min Range: -0.8766

Max Act: 0.6976. Min Act: -0.0001

Data Index: 1372169 (Python Code)

Max Activating Token Index: 373