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

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

Neuron 3046 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: 9.1910. Min Range: -9.1910

Max Act: 9.1910. Min Act: -0.0002

Data Index: 282056 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 9.1910. Min Range: -9.1910

Max Act: 9.0561. Min Act: -0.0002

Data Index: 203396 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 9.1910. Min Range: -9.1910

Max Act: 9.0105. Min Act: -0.0002

Data Index: 1142526 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.9525. Min Act: -0.0002

Data Index: 1182727 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.9820. Min Act: -0.0002

Data Index: 517690 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.9095. Min Act: -0.0002

Data Index: 1026097 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.9335. Min Act: -0.0002

Data Index: 1174601 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.9911. Min Act: -0.0002

Data Index: 879766 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.9644. Min Act: -0.0002

Data Index: 1449824 (Python Code)

Max Activating Token Index: 693

Text #9

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.9933. Min Act: -0.0002

Data Index: 1278242 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8552. Min Act: -0.0002

Data Index: 835416 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8453. Min Act: -0.0002

Data Index: 1457432 (Python Code)

Max Activating Token Index: 707

Text #12

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8559. Min Act: -0.0002

Data Index: 1157234 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8835. Min Act: -0.0002

Data Index: 1273931 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8116. Min Act: -0.0002

Data Index: 818557 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8229. Min Act: -0.0002

Data Index: 601136 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8626. Min Act: -0.0002

Data Index: 620959 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.9115. Min Act: -0.0002

Data Index: 324536 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8008. Min Act: -0.0002

Data Index: 955632 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 9.1910. Min Range: -9.1910

Max Act: 8.8548. Min Act: -0.0001

Data Index: 993493 (C4 (Web Text))

Max Activating Token Index: 905