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

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

Neuron 1702 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: 3.7521. Min Range: -3.7521

Max Act: 3.7521. Min Act: -0.1700

Data Index: 1597949 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6331. Min Act: -0.1700

Data Index: 448585 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6352. Min Act: -0.1700

Data Index: 1642696 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6397. Min Act: -0.1700

Data Index: 1464406 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.6297. Min Act: -0.1700

Data Index: 424217 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5685. Min Act: -0.1700

Data Index: 1362171 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5464. Min Act: -0.1700

Data Index: 1598521 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5529. Min Act: -0.1700

Data Index: 1425591 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5445. Min Act: -0.1700

Data Index: 1421152 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5337. Min Act: -0.1700

Data Index: 1400558 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5192. Min Act: -0.1700

Data Index: 1607984 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5182. Min Act: -0.1700

Data Index: 1374860 (Python Code)

Max Activating Token Index: 337

Text #12

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5094. Min Act: -0.1700

Data Index: 1380797 (Python Code)

Max Activating Token Index: 656

Text #13

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5118. Min Act: -0.1700

Data Index: 1640060 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.5050. Min Act: -0.1700

Data Index: 1603562 (Python Code)

Max Activating Token Index: 175

Text #15

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4973. Min Act: -0.1700

Data Index: 1639496 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4919. Min Act: -0.1700

Data Index: 1583024 (Python Code)

Max Activating Token Index: 699

Text #17

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1433610 (Python Code)

Max Activating Token Index: 128

Text #18

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4770. Min Act: -0.1700

Data Index: 1518356 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 3.7521. Min Range: -3.7521

Max Act: 3.4968. Min Act: -0.1700

Data Index: 1361231 (Python Code)

Max Activating Token Index: 246