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

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

Neuron 1245 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: 3.1165. Min Range: -3.1165

Max Act: 3.1141. Min Act: -0.1700

Data Index: 1495871 (Python Code)

Max Activating Token Index: 836

Text #1

Max Range: 3.1165. Min Range: -3.1165

Max Act: 3.1165. Min Act: -0.1700

Data Index: 1377655 (Python Code)

Max Activating Token Index: 467

Text #2

Max Range: 3.1165. Min Range: -3.1165

Max Act: 3.0719. Min Act: -0.1700

Data Index: 1452448 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 3.1165. Min Range: -3.1165

Max Act: 3.0605. Min Act: -0.1700

Data Index: 1643511 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 3.1165. Min Range: -3.1165

Max Act: 3.0029. Min Act: -0.1700

Data Index: 1476043 (Python Code)

Max Activating Token Index: 649

Text #5

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.9717. Min Act: -0.1700

Data Index: 1533323 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.9699. Min Act: -0.1700

Data Index: 1628748 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.9623. Min Act: -0.1700

Data Index: 1552849 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.9480. Min Act: -0.1700

Data Index: 1637286 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.9411. Min Act: -0.1700

Data Index: 1417001 (Python Code)

Max Activating Token Index: 497

Text #10

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.9290. Min Act: -0.1700

Data Index: 1446769 (Python Code)

Max Activating Token Index: 945

Text #11

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.9105. Min Act: -0.1700

Data Index: 1551347 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.9034. Min Act: -0.1700

Data Index: 1604015 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.8972. Min Act: -0.1700

Data Index: 649774 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.8831. Min Act: -0.1700

Data Index: 1469188 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.8837. Min Act: -0.1700

Data Index: 1438735 (Python Code)

Max Activating Token Index: 709

Text #16

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.8611. Min Act: -0.1700

Data Index: 1567349 (Python Code)

Max Activating Token Index: 839

Text #17

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.8661. Min Act: -0.1700

Data Index: 1600570 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.8908. Min Act: -0.1700

Data Index: 1578295 (Python Code)

Max Activating Token Index: 1015

Text #19

Max Range: 3.1165. Min Range: -3.1165

Max Act: 2.8650. Min Act: -0.1700

Data Index: 1394527 (Python Code)

Max Activating Token Index: 754