Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1050 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1629592 (Python Code)

Max Activating Token Index: 488

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1489004 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1407985 (Python Code)

Max Activating Token Index: 860

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1399177 (Python Code)

Max Activating Token Index: 503

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1497259 (Python Code)

Max Activating Token Index: 451

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1430558 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0162. Min Act: -0.0002

Data Index: 303943 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0155. Min Act: -0.0002

Data Index: 490748 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0153. Min Act: -0.0002

Data Index: 938686 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0150. Min Act: -0.0003

Data Index: 18968 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1512076 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0153. Min Act: -0.0002

Data Index: 444212 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0146. Min Act: -0.0002

Data Index: 770100 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0147. Min Act: -0.0002

Data Index: 552025 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0143. Min Act: -0.0002

Data Index: 52334 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0139. Min Act: -0.0002

Data Index: 279196 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1555339 (Python Code)

Max Activating Token Index: 653

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1346380 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1235857 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1227317 (C4 (Web Text))

Max Activating Token Index: 290