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

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

Neuron 1635 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3786. Min Range: -4.3786

Max Act: 4.3786. Min Act: -0.0001

Data Index: 438313 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.8739. Min Act: -0.0000

Data Index: 196593 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 4.3786. Min Range: -4.3786

Max Act: 4.0271. Min Act: -0.0000

Data Index: 984414 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.8246. Min Act: -0.0000

Data Index: 643020 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.7101. Min Act: -0.0000

Data Index: 351392 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.4588. Min Act: -0.0000

Data Index: 1254009 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.5547. Min Act: -0.0001

Data Index: 92296 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.5278. Min Act: -0.0001

Data Index: 298127 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.4756. Min Act: -0.0000

Data Index: 7086 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.5629. Min Act: -0.0000

Data Index: 280667 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.5768. Min Act: -0.0000

Data Index: 1019639 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.3483. Min Act: -0.0001

Data Index: 604214 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.1821. Min Act: -0.0000

Data Index: 763086 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.2094. Min Act: -0.0001

Data Index: 442187 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.1613. Min Act: -0.0000

Data Index: 533287 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.1530. Min Act: -0.0000

Data Index: 774605 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 4.3786. Min Range: -4.3786

Max Act: 3.1136. Min Act: -0.0000

Data Index: 222197 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.9754. Min Act: -0.0001

Data Index: 1235698 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.8187. Min Act: -0.0000

Data Index: 224566 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 4.3786. Min Range: -4.3786

Max Act: 2.9717. Min Act: -0.0000

Data Index: 719374 (C4 (Web Text))

Max Activating Token Index: 94