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

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

Neuron 1003 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: 3.5170. Min Range: -3.5170

Max Act: 3.5170. Min Act: -0.1700

Data Index: 1292668 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2876. Min Act: -0.1700

Data Index: 934702 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2814. Min Act: -0.1700

Data Index: 1428462 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2727. Min Act: -0.1700

Data Index: 1173927 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2683. Min Act: -0.1700

Data Index: 230440 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2692. Min Act: -0.1700

Data Index: 809051 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2532. Min Act: -0.1700

Data Index: 338943 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2587. Min Act: -0.1700

Data Index: 952545 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2366. Min Act: -0.1700

Data Index: 697032 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1874. Min Act: -0.1700

Data Index: 16305 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.2029. Min Act: -0.1700

Data Index: 482164 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1940. Min Act: -0.1700

Data Index: 1037896 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1793. Min Act: -0.1700

Data Index: 1577269 (Python Code)

Max Activating Token Index: 671

Text #13

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1572. Min Act: -0.1700

Data Index: 530011 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1566. Min Act: -0.1700

Data Index: 336492 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1652. Min Act: -0.1700

Data Index: 421940 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1629. Min Act: -0.1700

Data Index: 408808 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1622. Min Act: -0.1700

Data Index: 638554 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1593. Min Act: -0.1700

Data Index: 96248 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.5170. Min Range: -3.5170

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1566046 (Python Code)

Max Activating Token Index: 9