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

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

Neuron 1931 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: 3.3356. Min Range: -3.3356

Max Act: 3.3356. Min Act: -0.1700

Data Index: 1024660 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.3042. Min Act: -0.1700

Data Index: 575312 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2885. Min Act: -0.1700

Data Index: 51209 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2728. Min Act: -0.1700

Data Index: 1307094 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2885. Min Act: -0.1700

Data Index: 354257 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2885. Min Act: -0.1700

Data Index: 369281 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2570. Min Act: -0.1700

Data Index: 221249 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2570. Min Act: -0.1700

Data Index: 1025877 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2728. Min Act: -0.1700

Data Index: 934463 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2885. Min Act: -0.1700

Data Index: 522715 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2570. Min Act: -0.1700

Data Index: 835720 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2570. Min Act: -0.1700

Data Index: 826021 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2728. Min Act: -0.1700

Data Index: 1165216 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2413. Min Act: -0.1700

Data Index: 452756 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2570. Min Act: -0.1700

Data Index: 964774 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2256. Min Act: -0.1700

Data Index: 288504 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2256. Min Act: -0.1700

Data Index: 1267054 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2413. Min Act: -0.1700

Data Index: 238764 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2256. Min Act: -0.1700

Data Index: 635729 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 3.3356. Min Range: -3.3356

Max Act: 3.2256. Min Act: -0.1700

Data Index: 149733 (C4 (Web Text))

Max Activating Token Index: 491