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

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

Neuron 1380 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: 3.6656. Min Range: -3.6656

Max Act: 3.6656. Min Act: -0.1700

Data Index: 1335050 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.6103. Min Act: -0.1700

Data Index: 1077909 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.5454. Min Act: -0.1700

Data Index: 932669 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.5514. Min Act: -0.1700

Data Index: 643204 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.5079. Min Act: -0.1700

Data Index: 806582 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4860. Min Act: -0.1700

Data Index: 1047814 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4874. Min Act: -0.1700

Data Index: 1292797 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4934. Min Act: -0.1700

Data Index: 574045 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4815. Min Act: -0.1700

Data Index: 1078903 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4786. Min Act: -0.1700

Data Index: 781773 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4796. Min Act: -0.1700

Data Index: 848988 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4782. Min Act: -0.1700

Data Index: 986140 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4584. Min Act: -0.1700

Data Index: 232985 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4447. Min Act: -0.1700

Data Index: 825418 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4635. Min Act: -0.1700

Data Index: 657085 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4681. Min Act: -0.1700

Data Index: 995946 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4572. Min Act: -0.1700

Data Index: 97240 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4905. Min Act: -0.1700

Data Index: 695928 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4458. Min Act: -0.1700

Data Index: 803122 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 3.6656. Min Range: -3.6656

Max Act: 3.4585. Min Act: -0.1700

Data Index: 985441 (C4 (Web Text))

Max Activating Token Index: 499