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

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

Neuron 527 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5334. Min Range: -4.5334

Max Act: 4.5334. Min Act: -0.0000

Data Index: 832617 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.5659. Min Act: -0.0000

Data Index: 1092786 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.4294. Min Act: -0.0000

Data Index: 1183074 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.1563. Min Act: -0.0000

Data Index: 288946 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.3730. Min Act: -0.0000

Data Index: 684337 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.2172. Min Act: -0.0000

Data Index: 1166463 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.0774. Min Act: -0.0000

Data Index: 601221 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.1990. Min Act: -0.0000

Data Index: 407290 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.2333. Min Act: -0.0000

Data Index: 1008042 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.1618. Min Act: -0.0000

Data Index: 466771 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.9616. Min Act: -0.0000

Data Index: 89027 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.8138. Min Act: -0.0000

Data Index: 1073899 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 4.5334. Min Range: -4.5334

Max Act: 3.0439. Min Act: -0.0000

Data Index: 642512 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.6704. Min Act: -0.0000

Data Index: 108905 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.7708. Min Act: -0.0000

Data Index: 989405 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.8616. Min Act: -0.0000

Data Index: 360403 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.6066. Min Act: -0.0000

Data Index: 417559 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.9807. Min Act: -0.0000

Data Index: 475433 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.9113. Min Act: -0.0000

Data Index: 395132 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 4.5334. Min Range: -4.5334

Max Act: 2.6554. Min Act: -0.0000

Data Index: 319290 (C4 (Web Text))

Max Activating Token Index: 401