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

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

Neuron 172 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0181. Min Act: -0.0002

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1514241 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0145. Min Act: -0.0002

Data Index: 392918 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1536105 (Python Code)

Max Activating Token Index: 464

Text #4

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1047017 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0137. Min Act: -0.0002

Data Index: 443806 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1297736 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1308839 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1558989 (Python Code)

Max Activating Token Index: 480

Text #9

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0129. Min Act: -0.0002

Data Index: 712025 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1211425 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0130. Min Act: -0.0002

Data Index: 69950 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1606206 (Python Code)

Max Activating Token Index: 825

Text #13

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1069920 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0128. Min Act: -0.0002

Data Index: 850529 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0125. Min Act: -0.0002

Data Index: 425049 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1364853 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1465950 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0125. Min Act: -0.0002

Data Index: 146036 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0122. Min Act: -0.0002

Data Index: 296303 (C4 (Web Text))

Max Activating Token Index: 416