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

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

Neuron 3426 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: 0.0761. Min Range: -0.0761

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1286470 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0751. Min Act: -0.0003

Data Index: 25941 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0751. Min Act: -0.0002

Data Index: 72071 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0759. Min Act: -0.0002

Data Index: 161772 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0752. Min Act: -0.0002

Data Index: 310715 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0747. Min Act: -0.0002

Data Index: 378064 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0723. Min Act: -0.0003

Data Index: 910593 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1300424 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0716. Min Act: -0.0002

Data Index: 192458 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0705. Min Act: -0.0002

Data Index: 665442 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1071047 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1134887 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0694. Min Act: -0.0002

Data Index: 571402 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0692. Min Act: -0.0002

Data Index: 395701 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0672. Min Act: -0.0002

Data Index: 289507 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0675. Min Act: -0.0002

Data Index: 218803 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1259012 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1321207 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0685. Min Act: -0.0002

Data Index: 420557 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0660. Min Act: -0.0002

Data Index: 815780 (C4 (Web Text))

Max Activating Token Index: 131