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

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

Neuron 189 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.8335. Min Act: -0.1700

Data Index: 101168 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.8335. Min Act: -0.1700

Data Index: 875846 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.8022. Min Act: -0.1700

Data Index: 968907 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.8022. Min Act: -0.1700

Data Index: 118441 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7710. Min Act: -0.1700

Data Index: 306459 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7710. Min Act: -0.1700

Data Index: 861756 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7397. Min Act: -0.1700

Data Index: 763273 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7397. Min Act: -0.1700

Data Index: 702444 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7084. Min Act: -0.1700

Data Index: 1201049 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7084. Min Act: -0.1700

Data Index: 251068 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7397. Min Act: -0.1700

Data Index: 808274 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7397. Min Act: -0.1700

Data Index: 225198 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7084. Min Act: -0.1700

Data Index: 200625 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7084. Min Act: -0.1700

Data Index: 801557 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7397. Min Act: -0.1700

Data Index: 1020673 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6771. Min Act: -0.1700

Data Index: 932420 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6771. Min Act: -0.1700

Data Index: 701319 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6771. Min Act: -0.1700

Data Index: 275765 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7397. Min Act: -0.1700

Data Index: 617602 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7084. Min Act: -0.1700

Data Index: 266631 (C4 (Web Text))

Max Activating Token Index: 103