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

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

Neuron 5316 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0526. Min Range: -2.0526

Max Act: 2.0526. Min Act: -0.0000

Data Index: 522580 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.9280. Min Act: -0.0000

Data Index: 53835 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.8558. Min Act: -0.0000

Data Index: 973246 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.6462. Min Act: -0.0000

Data Index: 338248 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.8379. Min Act: -0.0000

Data Index: 269113 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.8701. Min Act: -0.0000

Data Index: 545819 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7163. Min Act: -0.0000

Data Index: 960512 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.6401. Min Act: -0.0000

Data Index: 974977 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.7187. Min Act: -0.0000

Data Index: 964963 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1196716 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.5643. Min Act: -0.0000

Data Index: 553774 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.5262. Min Act: -0.0000

Data Index: 887998 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.4328. Min Act: -0.0000

Data Index: 845106 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1126768 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.4175. Min Act: -0.0000

Data Index: 558006 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.3780. Min Act: -0.0000

Data Index: 633590 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.3730. Min Act: -0.0000

Data Index: 607178 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.4460. Min Act: -0.0000

Data Index: 923432 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.5397. Min Act: -0.0000

Data Index: 698198 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 2.0526. Min Range: -2.0526

Max Act: 1.4452. Min Act: -0.0000

Data Index: 1206567 (C4 (Web Text))

Max Activating Token Index: 69