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

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

Neuron 4394 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6879. Min Act: -0.0000

Data Index: 425185 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6134. Min Act: -0.0000

Data Index: 927558 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5563. Min Act: -0.0000

Data Index: 937680 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1003752 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5961. Min Act: -0.0000

Data Index: 620276 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1096711 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5761. Min Act: -0.0000

Data Index: 42765 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5200. Min Act: -0.0000

Data Index: 501009 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1223072 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1337407 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5386. Min Act: -0.0000

Data Index: 247348 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1396377 (Python Code)

Max Activating Token Index: 110

Text #12

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1418005 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1359345 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1639419 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1573965 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1459401 (Python Code)

Max Activating Token Index: 116

Text #17

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1425432 (Python Code)

Max Activating Token Index: 405

Text #18

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1642535 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5139. Min Act: -0.0000

Data Index: 403161 (C4 (Web Text))

Max Activating Token Index: 88