Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1570 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.5121. Min Act: -0.1700

Data Index: 1116163 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4494. Min Act: -0.1700

Data Index: 623039 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4651. Min Act: -0.1700

Data Index: 1487396 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4180. Min Act: -0.1700

Data Index: 658733 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4180. Min Act: -0.1700

Data Index: 892369 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4337. Min Act: -0.1700

Data Index: 209642 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4180. Min Act: -0.1700

Data Index: 990677 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4180. Min Act: -0.1700

Data Index: 511667 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4023. Min Act: -0.1700

Data Index: 727013 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3867. Min Act: -0.1700

Data Index: 860859 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3867. Min Act: -0.1700

Data Index: 699704 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.4023. Min Act: -0.1700

Data Index: 188908 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3710. Min Act: -0.1700

Data Index: 879030 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3710. Min Act: -0.1700

Data Index: 204912 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3710. Min Act: -0.1700

Data Index: 1233193 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3867. Min Act: -0.1700

Data Index: 662971 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3553. Min Act: -0.1700

Data Index: 1350764 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3396. Min Act: -0.1700

Data Index: 753777 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3710. Min Act: -0.1700

Data Index: 525385 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 3.5121. Min Range: -3.5121

Max Act: 3.3396. Min Act: -0.1700

Data Index: 1496851 (Python Code)

Max Activating Token Index: 3