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

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

Neuron 1501 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: 4.2860. Min Range: -4.2860

Max Act: 4.2860. Min Act: -0.1700

Data Index: 662884 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1767. Min Act: -0.1700

Data Index: 956531 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1720. Min Act: -0.1700

Data Index: 776183 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1076. Min Act: -0.1700

Data Index: 876376 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0748. Min Act: -0.1700

Data Index: 1067400 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0702. Min Act: -0.1700

Data Index: 1157209 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0759. Min Act: -0.1700

Data Index: 965955 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0530. Min Act: -0.1700

Data Index: 1082039 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0883. Min Act: -0.1700

Data Index: 756298 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0647. Min Act: -0.1700

Data Index: 867017 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0250. Min Act: -0.1700

Data Index: 932382 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0629. Min Act: -0.1700

Data Index: 299368 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0547. Min Act: -0.1700

Data Index: 672936 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0142. Min Act: -0.1700

Data Index: 809674 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0300. Min Act: -0.1700

Data Index: 329017 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0297. Min Act: -0.1700

Data Index: 707267 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0046. Min Act: -0.1700

Data Index: 731422 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0151. Min Act: -0.1700

Data Index: 130017 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0339. Min Act: -0.1700

Data Index: 876985 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0495. Min Act: -0.1700

Data Index: 237376 (C4 (Web Text))

Max Activating Token Index: 675