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

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

Neuron 2192 in Layer 0

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: 0.5672. Min Range: -0.5672

Max Act: 0.5672. Min Act: -0.0001

Data Index: 1618548 (Python Code)

Max Activating Token Index: 205

Text #1

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.5357. Min Act: -0.0001

Data Index: 1546491 (Python Code)

Max Activating Token Index: 936

Text #2

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4833. Min Act: -0.0002

Data Index: 1589189 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4814. Min Act: -0.0001

Data Index: 1572884 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4733. Min Act: -0.0001

Data Index: 1499678 (Python Code)

Max Activating Token Index: 427

Text #5

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4503. Min Act: -0.0001

Data Index: 1422318 (Python Code)

Max Activating Token Index: 485

Text #6

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4506. Min Act: -0.0001

Data Index: 1592990 (Python Code)

Max Activating Token Index: 124

Text #7

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1426526 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4267. Min Act: -0.0001

Data Index: 1502973 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4298. Min Act: -0.0001

Data Index: 1422030 (Python Code)

Max Activating Token Index: 197

Text #10

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4242. Min Act: -0.0001

Data Index: 1600846 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4095. Min Act: -0.0001

Data Index: 1512620 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4191. Min Act: -0.0001

Data Index: 1555169 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4112. Min Act: -0.0001

Data Index: 1464898 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3995. Min Act: -0.0001

Data Index: 1547747 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3923. Min Act: -0.0001

Data Index: 1444745 (Python Code)

Max Activating Token Index: 747

Text #16

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3920. Min Act: -0.0001

Data Index: 1368652 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3797. Min Act: -0.0001

Data Index: 1595463 (Python Code)

Max Activating Token Index: 595

Text #18

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1470643 (Python Code)

Max Activating Token Index: 569

Text #19

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3897. Min Act: -0.0001

Data Index: 1514799 (Python Code)

Max Activating Token Index: 148