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

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

Neuron 1665 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: 4.6646. Min Range: -4.6646

Max Act: 4.6646. Min Act: -0.1693

Data Index: 230915 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.4905. Min Act: -0.1700

Data Index: 264039 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.4429. Min Act: -0.1700

Data Index: 690074 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3949. Min Act: -0.1679

Data Index: 1181434 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3451. Min Act: -0.1697

Data Index: 1157713 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3547. Min Act: -0.1700

Data Index: 41673 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3555. Min Act: -0.1700

Data Index: 1107187 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3669. Min Act: -0.1686

Data Index: 755258 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3490. Min Act: -0.1395

Data Index: 463114 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3333. Min Act: -0.1700

Data Index: 203164 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3309. Min Act: -0.1700

Data Index: 567287 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3230. Min Act: -0.1700

Data Index: 938845 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3361. Min Act: -0.1699

Data Index: 435209 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3223. Min Act: -0.1691

Data Index: 236765 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3261. Min Act: -0.1697

Data Index: 967285 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3024. Min Act: -0.1700

Data Index: 1477008 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.2943. Min Act: -0.1700

Data Index: 378190 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.3128. Min Act: -0.1700

Data Index: 143785 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.2844. Min Act: -0.1699

Data Index: 45801 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.2790. Min Act: -0.1700

Data Index: 241792 (C4 (Web Text))

Max Activating Token Index: 886