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

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

Neuron 1629 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: 3.5303. Min Range: -3.5303

Max Act: 3.5303. Min Act: -0.1700

Data Index: 340613 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.3578. Min Act: -0.1700

Data Index: 1179200 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.3264. Min Act: -0.1700

Data Index: 535881 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.2950. Min Act: -0.1700

Data Index: 201096 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.2950. Min Act: -0.1700

Data Index: 600228 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1850. Min Act: -0.1700

Data Index: 526582 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1692. Min Act: -0.1700

Data Index: 996604 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.2007. Min Act: -0.1700

Data Index: 600942 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1377. Min Act: -0.1700

Data Index: 720166 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1692. Min Act: -0.1700

Data Index: 1139224 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1535. Min Act: -0.1700

Data Index: 833964 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1377. Min Act: -0.1700

Data Index: 15446 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1062. Min Act: -0.1700

Data Index: 10826 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1535. Min Act: -0.1700

Data Index: 165443 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1220. Min Act: -0.1700

Data Index: 745418 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1220. Min Act: -0.1700

Data Index: 754248 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1220. Min Act: -0.1700

Data Index: 354559 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1220. Min Act: -0.1700

Data Index: 595067 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1220. Min Act: -0.1700

Data Index: 279742 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 3.5303. Min Range: -3.5303

Max Act: 3.1220. Min Act: -0.1700

Data Index: 594018 (C4 (Web Text))

Max Activating Token Index: 342