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

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

Neuron 856 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0006

Data Index: 548973 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1573094 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0150. Min Act: -0.0006

Data Index: 257186 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0141. Min Act: -0.0006

Data Index: 885069 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0141. Min Act: -0.0006

Data Index: 939628 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0146. Min Act: -0.0006

Data Index: 779779 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0141. Min Act: -0.0006

Data Index: 241361 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0142. Min Act: -0.0006

Data Index: 379899 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1580364 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1565552 (Python Code)

Max Activating Token Index: 664

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1470405 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0134. Min Act: -0.0006

Data Index: 149441 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0133. Min Act: -0.0006

Data Index: 783096 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1501486 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1498979 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0130. Min Act: -0.0006

Data Index: 617340 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0125. Min Act: -0.0006

Data Index: 546705 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0124. Min Act: -0.0006

Data Index: 485055 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1575749 (Python Code)

Max Activating Token Index: 463

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1376779 (Python Code)

Max Activating Token Index: 671