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

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

Neuron 2029 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.6130. Min Act: -0.0000

Data Index: 570210 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1526352 (Python Code)

Max Activating Token Index: 490

Text #2

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1612855 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1542900 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5172. Min Act: -0.0000

Data Index: 687321 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1598697 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5429. Min Act: -0.0000

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5396. Min Act: -0.0000

Data Index: 546904 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1580781 (Python Code)

Max Activating Token Index: 990

Text #9

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1498566 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.6002. Min Act: -0.0000

Data Index: 664599 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4817. Min Act: -0.0000

Data Index: 590124 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.5091. Min Act: -0.0000

Data Index: 506481 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1008532 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1554053 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1629933 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4500. Min Act: -0.0000

Data Index: 108985 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1606967 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1524130 (Python Code)

Max Activating Token Index: 436

Text #19

Max Range: 0.6130. Min Range: -0.6130

Max Act: 0.4104. Min Act: -0.0000

Data Index: 898610 (C4 (Web Text))

Max Activating Token Index: 772