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

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

Neuron 622 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: 3.3030. Min Range: -3.3030

Max Act: 3.3030. Min Act: -0.1700

Data Index: 1062441 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.1878. Min Act: -0.1700

Data Index: 713147 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.1799. Min Act: -0.1700

Data Index: 1552921 (Python Code)

Max Activating Token Index: 762

Text #3

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.1662. Min Act: -0.1700

Data Index: 725641 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.1327. Min Act: -0.1700

Data Index: 1592689 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.1396. Min Act: -0.1700

Data Index: 229649 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.1290. Min Act: -0.1700

Data Index: 1598306 (Python Code)

Max Activating Token Index: 191

Text #7

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.1030. Min Act: -0.1700

Data Index: 1545847 (Python Code)

Max Activating Token Index: 529

Text #8

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0991. Min Act: -0.1700

Data Index: 808316 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.1169. Min Act: -0.1700

Data Index: 1517721 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0841. Min Act: -0.1700

Data Index: 440533 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0743. Min Act: -0.1700

Data Index: 1511004 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0985. Min Act: -0.1700

Data Index: 1388909 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0607. Min Act: -0.1700

Data Index: 1027402 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0725. Min Act: -0.1700

Data Index: 1125112 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0849. Min Act: -0.1700

Data Index: 971801 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0720. Min Act: -0.1700

Data Index: 791290 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0724. Min Act: -0.1700

Data Index: 674476 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0703. Min Act: -0.1700

Data Index: 1020914 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.3030. Min Range: -3.3030

Max Act: 3.0495. Min Act: -0.1700

Data Index: 1201892 (C4 (Web Text))

Max Activating Token Index: 902