Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4028 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0001

Data Index: 15117 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1251861 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1363224 (Python Code)

Max Activating Token Index: 917

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0146. Min Act: -0.0001

Data Index: 428745 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0153. Min Act: -0.0001

Data Index: 163110 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0151. Min Act: -0.0001

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1621066 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0146. Min Act: -0.0001

Data Index: 847799 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0133. Min Act: -0.0001

Data Index: 700587 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0141. Min Act: -0.0001

Data Index: 1240392 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0126. Min Act: -0.0001

Data Index: 550496 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0138. Min Act: -0.0001

Data Index: 882536 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0129. Min Act: -0.0001

Data Index: 740859 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0130. Min Act: -0.0001

Data Index: 637922 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0131. Min Act: -0.0001

Data Index: 934750 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1336528 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0121. Min Act: -0.0001

Data Index: 330263 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0136. Min Act: -0.0001

Data Index: 325170 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0131. Min Act: -0.0001

Data Index: 1387121 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0130. Min Act: -0.0001

Data Index: 554874 (C4 (Web Text))

Max Activating Token Index: 532