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

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

Neuron 5384 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: 1.7094. Min Range: -1.7094

Max Act: 1.6828. Min Act: -0.0002

Data Index: 1165413 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.7094. Min Act: -0.0002

Data Index: 768745 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.6639. Min Act: -0.0002

Data Index: 214946 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5989. Min Act: -0.0002

Data Index: 1048451 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.6027. Min Act: -0.0002

Data Index: 215376 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.6109. Min Act: -0.0002

Data Index: 654876 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5922. Min Act: -0.0002

Data Index: 823645 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5947. Min Act: -0.0002

Data Index: 641794 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5259. Min Act: -0.0002

Data Index: 984176 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4967. Min Act: -0.0002

Data Index: 1179295 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5321. Min Act: -0.0002

Data Index: 741076 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5337. Min Act: -0.0002

Data Index: 1342671 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.5096. Min Act: -0.0002

Data Index: 683264 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4776. Min Act: -0.0002

Data Index: 23673 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4790. Min Act: -0.0002

Data Index: 454895 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4827. Min Act: -0.0002

Data Index: 814720 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4823. Min Act: -0.0002

Data Index: 769688 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4236. Min Act: -0.0002

Data Index: 1347531 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4440. Min Act: -0.0002

Data Index: 88440 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.7094. Min Range: -1.7094

Max Act: 1.4625. Min Act: -0.0002

Data Index: 232226 (C4 (Web Text))

Max Activating Token Index: 345