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

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

Neuron 1143 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: 4.0182. Min Range: -4.0182

Max Act: 4.0182. Min Act: -0.1667

Data Index: 1528553 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.8774. Min Act: -0.1700

Data Index: 1451536 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1547138 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.7205. Min Act: -0.1700

Data Index: 596082 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.7013. Min Act: -0.1699

Data Index: 1617603 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6900. Min Act: -0.1667

Data Index: 1400218 (Python Code)

Max Activating Token Index: 579

Text #6

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6939. Min Act: -0.1700

Data Index: 34764 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6500. Min Act: -0.1700

Data Index: 1542010 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6696. Min Act: -0.1694

Data Index: 1649383 (Python Code)

Max Activating Token Index: 484

Text #9

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6610. Min Act: -0.1667

Data Index: 434729 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6645. Min Act: -0.1667

Data Index: 856702 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6643. Min Act: -0.1699

Data Index: 1619941 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6246. Min Act: -0.1697

Data Index: 1466081 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6280. Min Act: -0.1667

Data Index: 49135 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.6161. Min Act: -0.1699

Data Index: 1496768 (Python Code)

Max Activating Token Index: 1014

Text #15

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.5863. Min Act: -0.1699

Data Index: 1363090 (Python Code)

Max Activating Token Index: 1004

Text #16

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.5643. Min Act: -0.1700

Data Index: 1313021 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.5733. Min Act: -0.1700

Data Index: 1610004 (Python Code)

Max Activating Token Index: 864

Text #18

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.5654. Min Act: -0.1699

Data Index: 1529748 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 4.0182. Min Range: -4.0182

Max Act: 3.5541. Min Act: -0.1700

Data Index: 1414538 (Python Code)

Max Activating Token Index: 67