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

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

Neuron 1287 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: 4.2558. Min Range: -4.2558

Max Act: 4.2558. Min Act: -0.1700

Data Index: 529481 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.2131. Min Act: -0.1664

Data Index: 1245767 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1960. Min Act: -0.1700

Data Index: 892687 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1538. Min Act: -0.1699

Data Index: 340021 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1708. Min Act: -0.1696

Data Index: 128324 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1466. Min Act: -0.1700

Data Index: 360915 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1180. Min Act: -0.1700

Data Index: 272945 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1242. Min Act: -0.1686

Data Index: 565304 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1335. Min Act: -0.1699

Data Index: 1200744 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1326. Min Act: -0.1700

Data Index: 481518 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.1213. Min Act: -0.1699

Data Index: 1183993 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0846. Min Act: -0.1699

Data Index: 1318944 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0885. Min Act: -0.1700

Data Index: 1166583 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0947. Min Act: -0.1700

Data Index: 847569 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0837. Min Act: -0.1700

Data Index: 619979 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0541. Min Act: -0.1699

Data Index: 104281 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0024. Min Act: -0.1700

Data Index: 138115 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0010. Min Act: -0.1699

Data Index: 294753 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 4.2558. Min Range: -4.2558

Max Act: 4.0034. Min Act: -0.1694

Data Index: 398539 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 4.2558. Min Range: -4.2558

Max Act: 3.9979. Min Act: -0.1699

Data Index: 1135591 (C4 (Web Text))

Max Activating Token Index: 476