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

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

Neuron 4591 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1520880 (Python Code)

Max Activating Token Index: 231

Text #1

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1541968 (Python Code)

Max Activating Token Index: 388

Text #2

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1548086 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7166. Min Act: -0.0001

Data Index: 1510144 (Python Code)

Max Activating Token Index: 993

Text #4

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1588020 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1510843 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1407663 (Python Code)

Max Activating Token Index: 595

Text #7

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1647008 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1588239 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1602609 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1444669 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1496284 (Python Code)

Max Activating Token Index: 881

Text #12

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1511260 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1589263 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1603542 (Python Code)

Max Activating Token Index: 482

Text #15

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1505714 (Python Code)

Max Activating Token Index: 723

Text #16

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1580171 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1553717 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1655961 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 0.8119. Min Range: -0.8119

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1397290 (Python Code)

Max Activating Token Index: 758