Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 82 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1214. Min Range: -4.1214

Max Act: 4.1214. Min Act: -0.1700

Data Index: 1594254 (Python Code)

Max Activating Token Index: 732

Text #1

Max Range: 4.1214. Min Range: -4.1214

Max Act: 4.0312. Min Act: -0.1700

Data Index: 1480496 (Python Code)

Max Activating Token Index: 304

Text #2

Max Range: 4.1214. Min Range: -4.1214

Max Act: 4.0013. Min Act: -0.1697

Data Index: 1622313 (Python Code)

Max Activating Token Index: 149

Text #3

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.9784. Min Act: -0.1699

Data Index: 1608467 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.9509. Min Act: -0.1700

Data Index: 1465952 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8918. Min Act: -0.1700

Data Index: 1595567 (Python Code)

Max Activating Token Index: 607

Text #6

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.9242. Min Act: -0.1700

Data Index: 1388302 (Python Code)

Max Activating Token Index: 650

Text #7

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8938. Min Act: -0.1700

Data Index: 1599117 (Python Code)

Max Activating Token Index: 291

Text #8

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8996. Min Act: -0.1700

Data Index: 1464926 (Python Code)

Max Activating Token Index: 218

Text #9

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8976. Min Act: -0.1700

Data Index: 1575356 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8897. Min Act: -0.1700

Data Index: 1464133 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.9012. Min Act: -0.1700

Data Index: 1613287 (Python Code)

Max Activating Token Index: 728

Text #12

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8831. Min Act: -0.1700

Data Index: 1466262 (Python Code)

Max Activating Token Index: 724

Text #13

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8646. Min Act: -0.1700

Data Index: 1654112 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8575. Min Act: -0.1700

Data Index: 1635750 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8589. Min Act: -0.1700

Data Index: 1571784 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8583. Min Act: -0.1700

Data Index: 1464304 (Python Code)

Max Activating Token Index: 172

Text #17

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8615. Min Act: -0.1700

Data Index: 1572698 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8454. Min Act: -0.1700

Data Index: 1386143 (Python Code)

Max Activating Token Index: 48

Text #19

Max Range: 4.1214. Min Range: -4.1214

Max Act: 3.8365. Min Act: -0.1700

Data Index: 1528418 (Python Code)

Max Activating Token Index: 392