Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2037 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0005

Data Index: 30213 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0158. Min Act: -0.0005

Data Index: 929780 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0143. Min Act: -0.0005

Data Index: 922448 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0146. Min Act: -0.0005

Data Index: 280057 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0137. Min Act: -0.0005

Data Index: 762957 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1383472 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1156086 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1116749 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0132. Min Act: -0.0006

Data Index: 389737 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0128. Min Act: -0.0005

Data Index: 97357 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0128. Min Act: -0.0005

Data Index: 457292 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0128. Min Act: -0.0006

Data Index: 269576 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0128. Min Act: -0.0005

Data Index: 234673 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0124. Min Act: -0.0005

Data Index: 1332726 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0123. Min Act: -0.0006

Data Index: 677552 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0125. Min Act: -0.0005

Data Index: 1278292 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0123. Min Act: -0.0005

Data Index: 1505763 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0125. Min Act: -0.0005

Data Index: 914382 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0125. Min Act: -0.0005

Data Index: 863839 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0124. Min Act: -0.0006

Data Index: 346670 (C4 (Web Text))

Max Activating Token Index: 740