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

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

Neuron 2015 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: 5.5525. Min Range: -5.5525

Max Act: 5.5525. Min Act: -0.1615

Data Index: 1502252 (Python Code)

Max Activating Token Index: 617

Text #1

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.5110. Min Act: -0.1652

Data Index: 1387650 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.3485. Min Act: -0.1695

Data Index: 1437809 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.2931. Min Act: -0.1700

Data Index: 1602585 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.2230. Min Act: -0.1700

Data Index: 1498366 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.2111. Min Act: -0.1700

Data Index: 1472511 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.1998. Min Act: -0.1698

Data Index: 326743 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.1753. Min Act: -0.1700

Data Index: 1524852 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.1707. Min Act: -0.1700

Data Index: 1379026 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.2000. Min Act: -0.1698

Data Index: 1282603 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.1368. Min Act: -0.1699

Data Index: 1453167 (Python Code)

Max Activating Token Index: 766

Text #11

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.1316. Min Act: -0.1700

Data Index: 1217354 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.0355. Min Act: -0.1700

Data Index: 1610881 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.0605. Min Act: -0.1700

Data Index: 1040892 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.0567. Min Act: -0.1700

Data Index: 1552021 (Python Code)

Max Activating Token Index: 996

Text #15

Max Range: 5.5525. Min Range: -5.5525

Max Act: 5.0562. Min Act: -0.1700

Data Index: 1508478 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 5.5525. Min Range: -5.5525

Max Act: 4.9654. Min Act: -0.1700

Data Index: 1127316 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 5.5525. Min Range: -5.5525

Max Act: 4.9053. Min Act: -0.1699

Data Index: 1433181 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 5.5525. Min Range: -5.5525

Max Act: 4.9016. Min Act: -0.1700

Data Index: 1632420 (Python Code)

Max Activating Token Index: 120

Text #19

Max Range: 5.5525. Min Range: -5.5525

Max Act: 4.9140. Min Act: -0.1700

Data Index: 1157171 (C4 (Web Text))

Max Activating Token Index: 530