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

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

Neuron 3394 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: 0.0708. Min Range: -0.0708

Max Act: 0.0707. Min Act: -0.0002

Data Index: 506424 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0003

Data Index: 219196 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0692. Min Act: -0.0003

Data Index: 789214 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0680. Min Act: -0.0002

Data Index: 997518 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0663. Min Act: -0.0003

Data Index: 589127 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0657. Min Act: -0.0002

Data Index: 802449 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0651. Min Act: -0.0003

Data Index: 561188 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0609. Min Act: -0.0002

Data Index: 257869 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0595. Min Act: -0.0002

Data Index: 480452 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0585. Min Act: -0.0002

Data Index: 248113 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0578. Min Act: -0.0002

Data Index: 430278 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0577. Min Act: -0.0002

Data Index: 392687 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0560. Min Act: -0.0002

Data Index: 522133 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1308157 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1029888 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0529. Min Act: -0.0002

Data Index: 438500 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0539. Min Act: -0.0002

Data Index: 589762 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0540. Min Act: -0.0003

Data Index: 273930 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0523. Min Act: -0.0003

Data Index: 423988 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1226778 (C4 (Web Text))

Max Activating Token Index: 60