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

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

Neuron 574 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: 8.6935. Min Range: -8.6935

Max Act: 8.6935. Min Act: -0.1700

Data Index: 1441702 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.6037. Min Act: -0.1700

Data Index: 1439799 (Python Code)

Max Activating Token Index: 422

Text #2

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.5857. Min Act: -0.1699

Data Index: 1645303 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.5659. Min Act: -0.1700

Data Index: 1456007 (Python Code)

Max Activating Token Index: 248

Text #4

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.4845. Min Act: -0.1700

Data Index: 1497193 (Python Code)

Max Activating Token Index: 460

Text #5

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.4146. Min Act: -0.1700

Data Index: 1588588 (Python Code)

Max Activating Token Index: 263

Text #6

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.3962. Min Act: -0.1700

Data Index: 1464217 (Python Code)

Max Activating Token Index: 932

Text #7

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.3758. Min Act: -0.1700

Data Index: 1449877 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.2111. Min Act: -0.1700

Data Index: 1438918 (Python Code)

Max Activating Token Index: 249

Text #9

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.2185. Min Act: -0.1700

Data Index: 1427208 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.2295. Min Act: -0.1700

Data Index: 1609964 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.0863. Min Act: -0.1700

Data Index: 1511721 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.0314. Min Act: -0.1700

Data Index: 1454703 (Python Code)

Max Activating Token Index: 795

Text #13

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.0406. Min Act: -0.1700

Data Index: 1369614 (Python Code)

Max Activating Token Index: 678

Text #14

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.0665. Min Act: -0.1700

Data Index: 1366544 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.0105. Min Act: -0.1700

Data Index: 1377288 (Python Code)

Max Activating Token Index: 765

Text #16

Max Range: 8.6935. Min Range: -8.6935

Max Act: 8.0192. Min Act: -0.1700

Data Index: 1546052 (Python Code)

Max Activating Token Index: 866

Text #17

Max Range: 8.6935. Min Range: -8.6935

Max Act: 7.9809. Min Act: -0.1700

Data Index: 1566174 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 8.6935. Min Range: -8.6935

Max Act: 7.9150. Min Act: -0.1700

Data Index: 1601958 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 8.6935. Min Range: -8.6935

Max Act: 7.9435. Min Act: -0.1700

Data Index: 1362002 (Python Code)

Max Activating Token Index: 755