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

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

Neuron 1535 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: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0003

Data Index: 456496 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1061120 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1315481 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1141477 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1489435 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1531874 (Python Code)

Max Activating Token Index: 196

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1307653 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1437908 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1600820 (Python Code)

Max Activating Token Index: 111

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0003

Data Index: 197807 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1381669 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0148. Min Act: -0.0003

Data Index: 318294 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0003

Data Index: 970258 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1572537 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1080148 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0145. Min Act: -0.0003

Data Index: 976318 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1202842 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0003

Data Index: 795603 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0145. Min Act: -0.0003

Data Index: 583976 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0144. Min Act: -0.0003

Data Index: 959508 (C4 (Web Text))

Max Activating Token Index: 143