Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3552 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.5162. Min Act: -0.0002

Data Index: 1225016 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.2047. Min Act: -0.0002

Data Index: 333871 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.2169. Min Act: -0.0002

Data Index: 694958 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.1812. Min Act: -0.0003

Data Index: 803741 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.0512. Min Act: -0.0002

Data Index: 700296 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.1488. Min Act: -0.0002

Data Index: 1112088 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.0800. Min Act: -0.0002

Data Index: 661466 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.1290. Min Act: -0.0002

Data Index: 1188554 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.0982. Min Act: -0.0002

Data Index: 885508 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.0111. Min Act: -0.0002

Data Index: 1140323 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 2.5162. Min Range: -2.5162

Max Act: 1.9968. Min Act: -0.0002

Data Index: 982668 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 2.5162. Min Range: -2.5162

Max Act: 1.9925. Min Act: -0.0002

Data Index: 74926 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.0933. Min Act: -0.0002

Data Index: 501571 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.0098. Min Act: -0.0002

Data Index: 1143578 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.0059. Min Act: -0.0002

Data Index: 644795 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 2.5162. Min Range: -2.5162

Max Act: 1.9513. Min Act: -0.0002

Data Index: 507373 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 2.5162. Min Range: -2.5162

Max Act: 2.0136. Min Act: -0.0002

Data Index: 1246451 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 2.5162. Min Range: -2.5162

Max Act: 1.9504. Min Act: -0.0002

Data Index: 597519 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 2.5162. Min Range: -2.5162

Max Act: 1.9196. Min Act: -0.0002

Data Index: 194272 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 2.5162. Min Range: -2.5162

Max Act: 1.9235. Min Act: -0.0002

Data Index: 465035 (C4 (Web Text))

Max Activating Token Index: 940