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

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

Neuron 1923 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1037068 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1178818 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.6178. Min Act: -0.0000

Data Index: 128530 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1193213 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1469977 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5075. Min Act: -0.0000

Data Index: 507962 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1418251 (Python Code)

Max Activating Token Index: 690

Text #7

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1652283 (Python Code)

Max Activating Token Index: 967

Text #8

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1370887 (Python Code)

Max Activating Token Index: 700

Text #9

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5883. Min Act: -0.0000

Data Index: 876797 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1395357 (Python Code)

Max Activating Token Index: 1022

Text #11

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5586. Min Act: -0.0001

Data Index: 914633 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1549866 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1493087 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1520536 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4887. Min Act: -0.0001

Data Index: 1342148 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4828. Min Act: -0.0001

Data Index: 468898 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1641934 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1076995 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4761. Min Act: -0.0000

Data Index: 132000 (C4 (Web Text))

Max Activating Token Index: 245